Daily Papers

We introduce a benchmark to evaluate the capability of AI to solve problems in theoretical physics, focusing on high-energy theory and cosmology. The first iteration of our benchmark consists of 57 problems of varying difficulty, from undergraduate to research level. These problems are novel in the sense that they do not come from public problem collections. We evaluate our data set on various open and closed language models, including o3-mini, o1, DeepSeek-R1, GPT-4o and versions of Llama and Qwen. While we find impressive progress in model performance with the most recent models, our research-level difficulty problems are mostly unsolved. We address challenges of auto-verifiability and grading, and discuss common failure modes. While currently state-of-the art models are still of limited use for researchers, our results show that AI assisted theoretical physics research may become possible in the near future. We discuss the main obstacles towards this goal and possible strategies to overcome them. The public problems and solutions, results for various models, and updates to the data set and score distribution, are available on the website of the dataset tpbench.org.

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks--which, differing from algorithms, are more flexible and can support different algorithms--including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To measure this, we introduce the Remote Labor Index (RLI), a broadly multi-sector benchmark comprising real-world, economically valuable projects designed to evaluate end-to-end agent performance in practical settings. AI agents perform near the floor on RLI, with the highest-performing agent achieving an automation rate of 2.5%. These results help ground discussions of AI automation in empirical evidence, setting a common basis for tracking AI impacts and enabling stakeholders to proactively navigate AI-driven labor automation.

We tasked 16 state-of-the-art large language models (LLMs) with estimating the likelihood of Artificial General Intelligence (AGI) emerging by 2030. To assess the quality of these forecasts, we implemented an automated peer review process (LLM-PR). The LLMs' estimates varied widely, ranging from 3% (Reka- Core) to 47.6% (GPT-4o), with a median of 12.5%. These estimates closely align with a recent expert survey that projected a 10% likelihood of AGI by 2027, underscoring the relevance of LLMs in forecasting complex, speculative scenarios. The LLM-PR process demonstrated strong reliability, evidenced by a high Intraclass Correlation Coefficient (ICC = 0.79), reflecting notable consistency in scoring across the models. Among the models, Pplx-70b-online emerged as the top performer, while Gemini-1.5-pro-api ranked the lowest. A cross-comparison with external benchmarks, such as LMSYS Chatbot Arena, revealed that LLM rankings remained consistent across different evaluation methods, suggesting that existing benchmarks may not encapsulate some of the skills relevant for AGI prediction. We further explored the use of weighting schemes based on external benchmarks, optimizing the alignment of LLMs' predictions with human expert forecasts. This analysis led to the development of a new, 'AGI benchmark' designed to highlight performance differences in AGI-related tasks. Our findings offer insights into LLMs' capabilities in speculative, interdisciplinary forecasting tasks and emphasize the growing need for innovative evaluation frameworks for assessing AI performance in complex, uncertain real-world scenarios.

Recent advancements in AI reasoning have driven substantial improvements across diverse tasks. A critical open question is whether these improvements also yields better knowledge transfer: the ability of models to communicate reasoning in ways humans can understand, apply, and learn from. To investigate this, we introduce Knowledge Integration and Transfer Evaluation (KITE), a conceptual and experimental framework for Human-AI knowledge transfer capabilities and conduct the first large-scale human study (N=118) explicitly designed to measure it. In our two-phase setup, humans first ideate with an AI on problem-solving strategies, then independently implement solutions, isolating model explanations' influence on human understanding. Our findings reveal that although model benchmark performance correlates with collaborative outcomes, this relationship is notably inconsistent, featuring significant outliers, indicating that knowledge transfer requires dedicated optimization. Our analysis identifies behavioral and strategic factors mediating successful knowledge transfer. We release our code, dataset, and evaluation framework to support future work on communicatively aligned models.

This paper presents the Korean National Educational Test Benchmark (KoNET), a new benchmark designed to evaluate Multimodal Generative AI Systems using Korean national educational tests. KoNET comprises four exams: the Korean Elementary General Educational Development Test (KoEGED), Middle (KoMGED), High (KoHGED), and College Scholastic Ability Test (KoCSAT). These exams are renowned for their rigorous standards and diverse questions, facilitating a comprehensive analysis of AI performance across different educational levels. By focusing on Korean, KoNET provides insights into model performance in less-explored languages. We assess a range of models - open-source, open-access, and closed APIs - by examining difficulties, subject diversity, and human error rates. The code and dataset builder will be made fully open-sourced at https://github.com/naver-ai/KoNET.

With the rapid adoption of LLM-based chatbots, there is a pressing need to evaluate what humans and LLMs can achieve together. However, standard benchmarks, such as MMLU, measure LLM capabilities in isolation (i.e., "AI-alone"). Here, we design and conduct a user study to convert MMLU questions into user-AI conversations, by seeding the user with the question and having them carry out a conversation with the LLM to answer their question. We release ChatBench, a new dataset with AI-alone, user-alone, and user-AI data for 396 questions and two LLMs, including 144K answers and 7,336 user-AI conversations. We find that AI-alone accuracy fails to predict user-AI accuracy, with significant differences across multiple subjects (math, physics, and moral reasoning), and we analyze the user-AI conversations to provide insight into how they diverge from AI-alone benchmarks. Finally, we show that fine-tuning a user simulator on a subset of ChatBench improves its ability to estimate user-AI accuracies, increasing correlation on held-out questions by more than 20 points, creating possibilities for scaling interactive evaluation.

Large Language Model (LLM) based Generative AI systems have seen significant progress in recent years. Integrating a knowledge retrieval architecture allows for seamless integration of private data into publicly available Generative AI systems using pre-trained LLM without requiring additional model fine-tuning. Moreover, Retrieval-Centric Generation (RCG) approach, a promising future research direction that explicitly separates roles of LLMs and retrievers in context interpretation and knowledge memorization, potentially leads to more efficient implementation. SimplyRetrieve is an open-source tool with the goal of providing a localized, lightweight, and user-friendly interface to these sophisticated advancements to the machine learning community. SimplyRetrieve features a GUI and API based RCG platform, assisted by a Private Knowledge Base Constructor and a Retrieval Tuning Module. By leveraging these capabilities, users can explore the potential of RCG for improving generative AI performance while maintaining privacy standards. The tool is available at https://github.com/RCGAI/SimplyRetrieve with an MIT license.

The release of ChatGPT in 2022 triggered a rapid surge in generative artificial intelligence mobile apps (i.e., Gen-AI apps). Despite widespread adoption, little is known about how end users perceive and evaluate these Gen-AI functionalities in practice. In this work, we conduct a user-centered analysis of 676,066 reviews from 173 Gen-AI apps on the Google Play Store. We introduce a four-phase methodology, SARA (Selection, Acquisition, Refinement, and Analysis), that enables the systematic extraction of user insights using prompt-based LLM techniques. First, we demonstrate the reliability of LLMs in topic extraction, achieving 91% accuracy through five-shot prompting and non-informative review filtering. Then, we apply this method to the informative reviews, identify the top 10 user-discussed topics (e.g., AI Performance, Content Quality, and Content Policy & Censorship) and analyze the key challenges and emerging opportunities. Finally, we examine how these topics evolve over time, offering insight into shifting user expectations and engagement patterns with Gen-AI apps. Based on our findings and observations, we present actionable implications for developers and researchers.

We introduce GAIA, a benchmark for General AI Assistants that, if solved, would represent a milestone in AI research. GAIA proposes real-world questions that require a set of fundamental abilities such as reasoning, multi-modality handling, web browsing, and generally tool-use proficiency. GAIA questions are conceptually simple for humans yet challenging for most advanced AIs: we show that human respondents obtain 92\% vs. 15\% for GPT-4 equipped with plugins. This notable performance disparity contrasts with the recent trend of LLMs outperforming humans on tasks requiring professional skills in e.g. law or chemistry. GAIA's philosophy departs from the current trend in AI benchmarks suggesting to target tasks that are ever more difficult for humans. We posit that the advent of Artificial General Intelligence (AGI) hinges on a system's capability to exhibit similar robustness as the average human does on such questions. Using GAIA's methodology, we devise 466 questions and their answer. We release our questions while retaining answers to 300 of them to power a leader-board available at https://huggingface.co/gaia-benchmark.

The learning from practice paradigm is crucial for developing capable Agentic AI systems, yet it is severely hampered by inefficient experience generation, a bottleneck especially pronounced in complex benchmarks like GAIA. To address this, we introduce AWorld, an open-source system engineered for large-scale agent-environment interaction. By distributing tasks across a cluster, AWorld accelerates experience collection by 14.6x compared to standard single-node, sequential execution. This critical speedup makes extensive reinforcement learning practical and scalable. Leveraging this capability, we trained a Qwen3-32B-based agent that significantly outperforms its base model, increasing its overall GAIA accuracy from 21.59% to 32.23%. On the benchmark's most challenging levels, our agent achieves a score of 16.33%, surpassing the performance of leading proprietary models. Our open-source system and resulting agent provide a practical blueprint for a complete agentic AI training pipeline, from efficient interaction to demonstrable model improvement.

Building trusted datasets is critical for transparent and responsible Medical AI (MAI) research, but creating even small, high-quality datasets can take years of effort from multidisciplinary teams. This process often delays AI benefits, as human-centric data creation and AI-centric model development are treated as separate, sequential steps. To overcome this, we propose ScaleMAI, an agent of AI-integrated data curation and annotation, allowing data quality and AI performance to improve in a self-reinforcing cycle and reducing development time from years to months. We adopt pancreatic tumor detection as an example. First, ScaleMAI progressively creates a dataset of 25,362 CT scans, including per-voxel annotations for benign/malignant tumors and 24 anatomical structures. Second, through progressive human-in-the-loop iterations, ScaleMAI provides Flagship AI Model that can approach the proficiency of expert annotators (30-year experience) in detecting pancreatic tumors. Flagship Model significantly outperforms models developed from smaller, fixed-quality datasets, with substantial gains in tumor detection (+14%), segmentation (+5%), and classification (72%) on three prestigious benchmarks. In summary, ScaleMAI transforms the speed, scale, and reliability of medical dataset creation, paving the way for a variety of impactful, data-driven applications.

AI explanations are often mentioned as a way to improve human-AI decision-making, but empirical studies have not found consistent evidence of explanations' effectiveness and, on the contrary, suggest that they can increase overreliance when the AI system is wrong. While many factors may affect reliance on AI support, one important factor is how decision-makers reconcile their own intuition -- beliefs or heuristics, based on prior knowledge, experience, or pattern recognition, used to make judgments -- with the information provided by the AI system to determine when to override AI predictions. We conduct a think-aloud, mixed-methods study with two explanation types (feature- and example-based) for two prediction tasks to explore how decision-makers' intuition affects their use of AI predictions and explanations, and ultimately their choice of when to rely on AI. Our results identify three types of intuition involved in reasoning about AI predictions and explanations: intuition about the task outcome, features, and AI limitations. Building on these, we summarize three observed pathways for decision-makers to apply their own intuition and override AI predictions. We use these pathways to explain why (1) the feature-based explanations we used did not improve participants' decision outcomes and increased their overreliance on AI, and (2) the example-based explanations we used improved decision-makers' performance over feature-based explanations and helped achieve complementary human-AI performance. Overall, our work identifies directions for further development of AI decision-support systems and explanation methods that help decision-makers effectively apply their intuition to achieve appropriate reliance on AI.

Developing AI systems that operate effectively across languages while remaining culturally grounded is a long-standing challenge, particularly in low-resource settings. Synthetic data provides a promising avenue, yet its effectiveness in multilingual and multicultural contexts remains underexplored. We investigate the creation and impact of synthetic, culturally contextualized datasets for Indian languages through a bottom-up generation strategy that prompts large open-source LLMs (>= 235B parameters) to ground data generation in language-specific Wikipedia content. This approach complements the dominant top-down paradigm of translating synthetic datasets from high-resource languages such as English. We introduce Updesh, a high-quality large-scale synthetic instruction-following dataset comprising 9.5M data points across 13 Indian languages, encompassing diverse reasoning and generative tasks with an emphasis on long-context, multi-turn capabilities, and alignment with Indian cultural contexts. A comprehensive evaluation incorporating both automated metrics and human annotation across 10k assessments indicates that generated data is high quality; though, human evaluation highlights areas for further improvement. Additionally, we perform downstream evaluations by fine-tuning models on our dataset and assessing the performance across 15 diverse multilingual datasets. Models trained on Updesh consistently achieve significant gains on generative tasks and remain competitive on multiple-choice style NLU tasks. Notably, relative improvements are most pronounced in low and medium-resource languages, narrowing their gap with high-resource languages. These findings provide empirical evidence that effective multilingual AI requires multi-faceted data curation and generation strategies that incorporate context-aware, culturally grounded methodologies.

In this position paper, we argue that human baselines in foundation model evaluations must be more rigorous and more transparent to enable meaningful comparisons of human vs. AI performance, and we provide recommendations and a reporting checklist towards this end. Human performance baselines are vital for the machine learning community, downstream users, and policymakers to interpret AI evaluations. Models are often claimed to achieve "super-human" performance, but existing baselining methods are neither sufficiently rigorous nor sufficiently well-documented to robustly measure and assess performance differences. Based on a meta-review of the measurement theory and AI evaluation literatures, we derive a framework with recommendations for designing, executing, and reporting human baselines. We synthesize our recommendations into a checklist that we use to systematically review 115 human baselines (studies) in foundation model evaluations and thus identify shortcomings in existing baselining methods; our checklist can also assist researchers in conducting human baselines and reporting results. We hope our work can advance more rigorous AI evaluation practices that can better serve both the research community and policymakers. Data is available at: https://github.com/kevinlwei/human-baselines

We present ReXVQA, the largest and most comprehensive benchmark for visual question answering (VQA) in chest radiology, comprising approximately 696,000 questions paired with 160,000 chest X-rays studies across training, validation, and test sets. Unlike prior efforts that rely heavily on template based queries, ReXVQA introduces a diverse and clinically authentic task suite reflecting five core radiological reasoning skills: presence assessment, location analysis, negation detection, differential diagnosis, and geometric reasoning. We evaluate eight state-of-the-art multimodal large language models, including MedGemma-4B-it, Qwen2.5-VL, Janus-Pro-7B, and Eagle2-9B. The best-performing model (MedGemma) achieves 83.24% overall accuracy. To bridge the gap between AI performance and clinical expertise, we conducted a comprehensive human reader study involving 3 radiology residents on 200 randomly sampled cases. Our evaluation demonstrates that MedGemma achieved superior performance (83.84% accuracy) compared to human readers (best radiology resident: 77.27%), representing a significant milestone where AI performance exceeds expert human evaluation on chest X-ray interpretation. The reader study reveals distinct performance patterns between AI models and human experts, with strong inter-reader agreement among radiologists while showing more variable agreement patterns between human readers and AI models. ReXVQA establishes a new standard for evaluating generalist radiological AI systems, offering public leaderboards, fine-grained evaluation splits, structured explanations, and category-level breakdowns. This benchmark lays the foundation for next-generation AI systems capable of mimicking expert-level clinical reasoning beyond narrow pathology classification. Our dataset will be open-sourced at https://huggingface.co/datasets/rajpurkarlab/ReXVQA

Humans have the ability to reason about geometric patterns in images and scenes from a young age. However, developing large multimodal models (LMMs) capable of similar reasoning remains a challenge, highlighting the need for robust evaluation methods to assess these capabilities. We introduce \Turtle, a benchmark designed to evaluate LMMs' capacity to interpret geometric patterns -- given visual examples, textual instructions, or both -- and generate precise code outputs. Inspired by turtle geometry, a notion used to teach children foundational coding and geometric concepts, TurtleBench features tasks with patterned shapes that have underlying algorithmic logic. Our evaluation reveals that leading LMMs struggle significantly with these tasks, with GPT-4o achieving only 19\% accuracy on the simplest tasks and few-shot prompting only marginally improves their performance (<2%). \Turtle highlights the gap between human and AI performance in intuitive and visual geometrical understanding, setting the stage for future research in this area. \Turtle stands as one of the few benchmarks to evaluate the integration of visual understanding and code generation capabilities in LMMs, setting the stage for future research. Code and Dataset for this paper is provided here: https://github.com/sinaris76/TurtleBench{https://github.com/sinaris76/TurtleBench}

Tumor synthesis can generate examples that AI often misses or over-detects, improving AI performance by training on these challenging cases. However, existing synthesis methods, which are typically unconditional -- generating images from random variables -- or conditioned only by tumor shapes, lack controllability over specific tumor characteristics such as texture, heterogeneity, boundaries, and pathology type. As a result, the generated tumors may be overly similar or duplicates of existing training data, failing to effectively address AI's weaknesses. We propose a new text-driven tumor synthesis approach, termed TextoMorph, that provides textual control over tumor characteristics. This is particularly beneficial for examples that confuse the AI the most, such as early tumor detection (increasing Sensitivity by +8.5%), tumor segmentation for precise radiotherapy (increasing DSC by +6.3%), and classification between benign and malignant tumors (improving Sensitivity by +8.2%). By incorporating text mined from radiology reports into the synthesis process, we increase the variability and controllability of the synthetic tumors to target AI's failure cases more precisely. Moreover, TextoMorph uses contrastive learning across different texts and CT scans, significantly reducing dependence on scarce image-report pairs (only 141 pairs used in this study) by leveraging a large corpus of 34,035 radiology reports. Finally, we have developed rigorous tests to evaluate synthetic tumors, including Text-Driven Visual Turing Test and Radiomics Pattern Analysis, showing that our synthetic tumors is realistic and diverse in texture, heterogeneity, boundaries, and pathology.

In this paper, we propose the use of the popular word-based board game Codenames as a suitable benchmark for evaluating the reasoning capabilities of Large Language Models (LLMs). Codenames presents a highly interesting challenge for achieving successful AI performance, requiring both a sophisticated understanding of language, theory of mind, and epistemic reasoning capabilities. Prior attempts to develop agents for Codenames have largely relied on word embedding techniques, which have a limited vocabulary range and perform poorly when paired with differing approaches. LLMs have demonstrated enhanced reasoning and comprehension capabilities for language-based tasks, but can still suffer in lateral thinking challenges. We evaluate the capabilities of several state-of-the-art LLMs, including GPT-4o, Gemini 1.5, Claude 3.5 Sonnet, and Llama 3.1, across a variety of board setups. Our results indicate that while certain LLMs perform better than others overall, different models exhibit varying emergent behaviours during gameplay and excel at specific roles. We also evaluate the performance of different combinations of LLMs when playing cooperatively together, demonstrating that LLM agents are more generalisable to a wider range of teammates than prior techniques.

Humans are social beings; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We simulate the role-play interaction between LLM-based agents and humans within this task space and evaluate their performance with a holistic evaluation framework called SOTOPIA-Eval. With SOTOPIA, we find significant differences between these models in terms of their social intelligence, and we identify a subset of SOTOPIA scenarios, SOTOPIA-hard, that is generally challenging for all models. We find that on this subset, GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills. These findings demonstrate SOTOPIA's promise as a general platform for research on evaluating and improving social intelligence in artificial agents.

Large Language Models (LLMs) suffer significant performance degradation in multi-turn conversations when information is presented incrementally. Given that multi-turn conversations characterize everyday interactions with LLMs, this degradation poses a severe challenge to real world usability. We hypothesize that abrupt increases in model uncertainty signal misalignment in multi-turn LLM interactions, and we exploit this insight to dynamically realign conversational context. We introduce ERGO (Entropy-guided Resetting for Generation Optimization), which continuously quantifies internal uncertainty via Shannon entropy over next token distributions and triggers adaptive prompt consolidation when a sharp spike in entropy is detected. By treating uncertainty as a first class signal rather than a nuisance to eliminate, ERGO embraces variability in language and modeling, representing and responding to uncertainty. In multi-turn tasks with incrementally revealed instructions, ERGO yields a 56.6% average performance gain over standard baselines, increases aptitude (peak performance capability) by 24.7%, and decreases unreliability (variability in performance) by 35.3%, demonstrating that uncertainty aware interventions can improve both accuracy and reliability in conversational AI.

Tumor segmentation in CT scans is key for diagnosis, surgery, and prognosis, yet segmentation masks are scarce because their creation requires time and expertise. Public abdominal CT datasets have from dozens to a couple thousand tumor masks, but hospitals have hundreds of thousands of tumor CTs with radiology reports. Thus, leveraging reports to improve segmentation is key for scaling. In this paper, we propose a report-supervision loss (R-Super) that converts radiology reports into voxel-wise supervision for tumor segmentation AI. We created a dataset with 6,718 CT-Report pairs (from the UCSF Hospital), and merged it with public CT-Mask datasets (from AbdomenAtlas 2.0). We used our R-Super to train with these masks and reports, and strongly improved tumor segmentation in internal and external validation--F1 Score increased by up to 16% with respect to training with masks only. By leveraging readily available radiology reports to supplement scarce segmentation masks, R-Super strongly improves AI performance both when very few training masks are available (e.g., 50), and when many masks were available (e.g., 1.7K). Project: https://github.com/MrGiovanni/R-Super

Modern science emerged from reasoning over repeatedly-observed planetary motions. We present Gravity-Bench-v1, an environment-based benchmark that challenges AI agents on tasks that parallel this historical development. Gravity-Bench-v1 evaluates agents on the discovery of physics concealed within a dynamic environment, using rigorous gravitational dynamics simulations. Gravity-Bench includes out-of-distribution cases, i.e. with physics that deviates from the real world, to evaluate true scientific generalization capabilities. Agents must plan to collect data within an experimental budget and must perform a dynamic form of data analysis and reasoning to solve tasks efficiently. Our benchmark admits an open-ended space of solutions. PhD-level solutions for each task are provided, to calibrate AI performance against human expertise. Technically at an upper-undergraduate level, our benchmark proves challenging to baseline AI agents. Gravity-Bench-v1 and planned extensions should help map out AI progress towards scientific discovery capabilities.

This study investigates the efficacy of large language models (LLMs) as tools for grading master-level student essays. Utilizing a sample of 60 essays in political science, the study compares the accuracy of grades suggested by the GPT-4 model with those awarded by university teachers. Results indicate that while GPT-4 aligns with human grading standards on mean scores, it exhibits a risk-averse grading pattern and its interrater reliability with human raters is low. Furthermore, modifications in the grading instructions (prompt engineering) do not significantly alter AI performance, suggesting that GPT-4 primarily assesses generic essay characteristics such as language quality rather than adapting to nuanced grading criteria. These findings contribute to the understanding of AI's potential and limitations in higher education, highlighting the need for further development to enhance its adaptability and sensitivity to specific educational assessment requirements.

BACKGROUND: Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently the adoption of structured reporting (SR) has been recommended by various medical societies thanks to the advantages it offers, e.g. standardization, completeness and information retrieval. We propose a pipeline to extract information from free-text radiology reports, that fits with the items of the reference SR registry proposed by a national society of interventional and medical radiology, focusing on CT staging of patients with lymphoma. METHODS: Our work aims to leverage the potential of Natural Language Processing (NLP) and Transformer-based models to deal with automatic SR registry filling. With the availability of 174 radiology reports, we investigate a rule-free generative Question Answering approach based on a domain-specific version of T5 (IT5). Two strategies (batch-truncation and ex-post combination) are implemented to comply with the model's context length limitations. Performance is evaluated in terms of strict accuracy, F1, and format accuracy, and compared with the widely used GPT-3.5 Large Language Model. A 5-point Likert scale questionnaire is used to collect human-expert feedback on the similarity between medical annotations and generated answers. RESULTS: The combination of fine-tuning and batch splitting allows IT5 to achieve notable results; it performs on par with GPT-3.5 albeit its size being a thousand times smaller in terms of parameters. Human-based assessment scores show a high correlation (Spearman's correlation coefficients>0.88, p-values<0.001) with AI performance metrics (F1) and confirm the superior ability of LLMs (i.e., GPT-3.5, 175B of parameters) in generating plausible human-like statements.

Semantic Segmentation is a significant research field in Computer Vision. Despite being a widely studied subject area, many visualization tools do not exist that capture segmentation quality and dataset statistics such as a class imbalance in the same view. While the significance of discovering and introspecting the correlation between dataset statistics and AI model performance for dense prediction computer vision tasks such as semantic segmentation is well established in the computer vision literature, to the best of our knowledge, no visualization tools have been proposed to view and analyze the aforementioned tasks. Our project aims to bridge this gap by proposing three visualizations that enable users to compare dataset statistics and AI performance for segmenting all images, a single image in the dataset, explore the AI model's attention on image regions once trained and browse the quality of masks predicted by AI for any selected (by user) number of objects under the same tool. Our project tries to further increase the interpretability of the trained AI model for segmentation by visualizing its image attention weights. For visualization, we use Scatterplot and Heatmap to encode correlation and features, respectively. We further propose to conduct surveys on real users to study the efficacy of our visualization tool in computer vision and AI domain. The full system can be accessed at https://github.com/dipta007/SeeBel

Given the ubiquitous nature of numbers in text, reasoning with numbers to perform simple calculations is an important skill of AI systems. While many datasets and models have been developed to this end, state-of-the-art AI systems are brittle; failing to perform the underlying mathematical reasoning when they appear in a slightly different scenario. Drawing inspiration from GLUE that was proposed in the context of natural language understanding, we propose NumGLUE, a multi-task benchmark that evaluates the performance of AI systems on eight different tasks, that at their core require simple arithmetic understanding. We show that this benchmark is far from being solved with neural models including state-of-the-art large-scale language models performing significantly worse than humans (lower by 46.4%). Further, NumGLUE promotes sharing knowledge across tasks, especially those with limited training data as evidenced by the superior performance (average gain of 3.4% on each task) when a model is jointly trained on all the tasks as opposed to task-specific modeling. Finally, we hope that NumGLUE will encourage systems that perform robust and general arithmetic reasoning within language, a first step towards being able to perform more complex mathematical reasoning.

Spatial understanding over continuous visual input is crucial for MLLMs to evolve into general-purpose assistants in physical environments. Yet there is still no comprehensive benchmark that holistically assesses the progress toward this goal. In this work, we introduce MMSI-Video-Bench, a fully human-annotated benchmark for video-based spatial intelligence in MLLMs. It operationalizes a four-level framework, Perception, Planning, Prediction, and Cross-Video Reasoning, through 1,106 questions grounded in 1,278 clips from 25 datasets and in-house videos. Each item is carefully designed and reviewed by 3DV experts with explanatory rationales to ensure precise, unambiguous grounding. Leveraging its diverse data sources and holistic task coverage, MMSI-Video-Bench also supports three domain-oriented sub-benchmarks (Indoor Scene Perception Bench, Robot Bench and Grounding Bench) for targeted capability assessment. We evaluate 25 strong open-source and proprietary MLLMs, revealing a striking human--AI gap: many models perform near chance, and the best reasoning model lags humans by nearly 60%. We further find that spatially fine-tuned models still fail to generalize effectively on our benchmark. Fine-grained error analysis exposes systematic failures in geometric reasoning, motion grounding, long-horizon prediction, and cross-video correspondence. We also show that typical frame-sampling strategies transfer poorly to our reasoning-intensive benchmark, and that neither 3D spatial cues nor chain-of-thought prompting yields meaningful gains. We expect our benchmark to establish a solid testbed for advancing video-based spatial intelligence.

Legal compliance in AI-driven data transfer planning is becoming increasingly critical under stringent privacy regulations such as the Japanese Act on the Protection of Personal Information (APPI). We propose a multi-agent legal verifier that decomposes compliance checking into specialized agents for statutory interpretation, business context evaluation, and risk assessment, coordinated through a structured synthesis protocol. Evaluated on a stratified dataset of 200 Amended APPI Article 16 cases with clearly defined ground truth labels and multiple performance metrics, the system achieves 72% accuracy, which is 21 percentage points higher than a single-agent baseline, including 90% accuracy on clear compliance cases (vs. 16% for the baseline) while maintaining perfect detection of clear violations. While challenges remain in ambiguous scenarios, these results show that domain specialization and coordinated reasoning can meaningfully improve legal AI performance, providing a scalable and regulation-aware framework for trustworthy and interpretable automated compliance verification.

Exploiting sparsity underlying neural networks has become one of the most potential methodologies to reduce the memory footprint, I/O cost, and computation workloads during inference. And the degree of sparsity one can exploit has become higher as larger model sizes have been considered along with the trend of pre-training giant models. On the other hand, compared with quantization that has been a widely supported option, acceleration through high-degree sparsity is not supported in most computing platforms. In this work, we introduce the first commercial hardware platform supporting high-degree sparsity acceleration up to 32 times -- S4. Combined with state-of-the-art sparse pruning techniques, we demonstrate several-times practical inference speedup on S4 over mainstream inference platforms such as Nvidia T4. We also show that in practice a sparse model of larger size can achieve both higher accuracy and higher throughput on S4 than a dense model of smaller size.

State-of-the-art AI systems can be significantly improved without expensive retraining via "post-training enhancements"-techniques applied after initial training like fine-tuning the system to use a web browser. We review recent post-training enhancements, categorizing them into five types: tool-use, prompting methods, scaffolding, solution selection, and data generation. Different enhancements improve performance on different tasks, making it hard to compare their significance. So we translate improvements from different enhancements into a common currency, the compute-equivalent gain: how much additional training compute would be needed to improve performance by the same amount as the enhancement. Our non-experimental work shows that post-training enhancements have significant benefits: most surveyed enhancements improve benchmark performance by more than a 5x increase in training compute, some by more than 20x. Post-training enhancements are relatively cheap to develop: fine-tuning costs are typically <1% of the original training cost. Governing the development of capable post-training enhancements may be challenging because frontier models could be enhanced by a wide range of actors.

In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as a heavy reliance on precise descriptions for decision-making, and the lack of a systematic approach to leverage try-and-fail procedures akin to traditional Reinforcement Learning (RL). REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance. This approach has the advantage of enabling the utilization of offline behaviors from logs and allowing seamless integration with existing foundation models while it does not require any model fine-tuning. Through comparative analysis with existing methods such as Chain-of-Thoughts(CoT) and Reasoning viA Planning(RAP), REX-based methods demonstrate comparable performance and, in certain cases, even surpass the results achieved by these existing techniques. Notably, REX-based methods exhibit remarkable reductions in execution time, enhancing their practical applicability across a diverse set of scenarios.

Despite advances in AI's performance and interpretability, AI advisors can undermine experts' decisions and increase the time and effort experts must invest to make decisions. Consequently, AI systems deployed in high-stakes settings often fail to consistently add value across contexts and can even diminish the value that experts alone provide. Beyond harm in specific domains, such outcomes impede progress in research and practice, underscoring the need to understand when and why different AI advisors add or diminish value. To bridge this gap, we stress the importance of assessing the value AI advice brings to real-world contexts when designing and evaluating AI advisors. Building on this perspective, we characterize key pillars -- pathways through which AI advice impacts value -- and develop a framework that incorporates these pillars to create reliable, personalized, and value-adding advisors. Our results highlight the need for system-level, value-driven development of AI advisors that advise selectively, are tailored to experts' unique behaviors, and are optimized for context-specific trade-offs between decision improvements and advising costs. They also reveal how the lack of inclusion of these pillars in the design of AI advising systems may be contributing to the failures observed in practical applications.

To generate evidence regarding the safety and efficacy of artificial intelligence (AI) enabled medical devices, AI models need to be evaluated on a diverse population of patient cases, some of which may not be readily available. We propose an evaluation approach for testing medical imaging AI models that relies on in silico imaging pipelines in which stochastic digital models of human anatomy (in object space) with and without pathology are imaged using a digital replica imaging acquisition system to generate realistic synthetic image datasets. Here, we release M-SYNTH, a dataset of cohorts with four breast fibroglandular density distributions imaged at different exposure levels using Monte Carlo x-ray simulations with the publicly available Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE) toolkit. We utilize the synthetic dataset to analyze AI model performance and find that model performance decreases with increasing breast density and increases with higher mass density, as expected. As exposure levels decrease, AI model performance drops with the highest performance achieved at exposure levels lower than the nominal recommended dose for the breast type.

The rapid advancement of video generation models has made it increasingly challenging to distinguish AI-generated videos from real ones. This issue underscores the urgent need for effective AI-generated video detectors to prevent the dissemination of false information via such videos. However, the development of high-performance AI-generated video detectors is currently impeded by the lack of large-scale, high-quality datasets specifically designed for generative video detection. To this end, we introduce GenVidBench, a challenging AI-generated video detection dataset with several key advantages: 1) Large-scale video collection: The dataset contains 6.78 million videos and is currently the largest dataset for AI-generated video detection. 2) Cross-Source and Cross-Generator: The cross-source generation reduces the interference of video content on the detection. The cross-generator ensures diversity in video attributes between the training and test sets, preventing them from being overly similar. 3) State-of-the-Art Video Generators: The dataset includes videos from 11 state-of-the-art AI video generators, ensuring that it covers the latest advancements in the field of video generation. These generators ensure that the datasets are not only large in scale but also diverse, aiding in the development of generalized and effective detection models. Additionally, we present extensive experimental results with advanced video classification models. With GenVidBench, researchers can efficiently develop and evaluate AI-generated video detection models.. Datasets and code are available at https://genvidbench.github.io.

AI models are increasingly used for data analysis and visualization, yet benchmarks rarely address scatterplot-specific tasks, limiting insight into performance. To address this gap for one of the most common chart types, we introduce a synthetic, annotated dataset of over 18,000 scatterplots from six data generators and 17 chart designs, and a benchmark based on it. We evaluate proprietary models from OpenAI and Google using N-shot prompting on five distinct tasks derived from annotations of cluster bounding boxes, their center coordinates, and outlier coordinates. OpenAI models and Gemini 2.5 Flash, especially when prompted with examples, are viable options for counting clusters and, in Flash's case, outliers (90%+ Accuracy). However, the results for localization-related tasks are unsatisfactory: Precision and Recall are near or below 50%, except for Flash in outlier identification (65.01%). Furthermore, the impact of chart design on performance appears to be a secondary factor, but it is advisable to avoid scatterplots with wide aspect ratios (16:9 and 21:9) or those colored randomly. Supplementary materials are available at https://github.com/feedzai/biy-paper.

Frontier AI development relies on powerful AI supercomputers, yet analysis of these systems is limited. We create a dataset of 500 AI supercomputers from 2019 to 2025 and analyze key trends in performance, power needs, hardware cost, ownership, and global distribution. We find that the computational performance of AI supercomputers has doubled every nine months, while hardware acquisition cost and power needs both doubled every year. The leading system in March 2025, xAI's Colossus, used 200,000 AI chips, had a hardware cost of \7B, and required 300 MW of power, as much as 250,000 households. As AI supercomputers evolved from tools for science to industrial machines, companies rapidly expanded their share of total AI supercomputer performance, while the share of governments and academia diminished. Globally, the United States accounts for about 75% of total performance in our dataset, with China in second place at 15%. If the observed trends continue, the leading AI supercomputer in 2030 will achieve 2\times10^{22} 16-bit FLOP/s, use two million AI chips, have a hardware cost of 200 billion, and require 9 GW of power. Our analysis provides visibility into the AI supercomputer landscape, allowing policymakers to assess key AI trends like resource needs, ownership, and national competitiveness.

There have been multiple calls for investments in the development of AI standards that both preserve the transformative potential and minimize the risks of AI. The goals of AI standards, particularly with respect to AI data, performance, and governance, are to promote innovation and public trust in systems that use AI. However, there is a lack of a formal or shared method to measure the impact of these standardization activities on the goals of innovation and trust. This concept paper proposes an analytical approach that could inform the evaluation of the impact of AI standards. The proposed approach could be used to measure, assess, and eventually evaluate the extent to which AI standards achieve their stated goals, since most Standards Development Organizationss do not track the impact of their standards once completed. It is intended to stimulate discussions with a wide variety of stakeholders, including academia and the standards community, about the potential for the approach to evaluate the effectiveness, utility, and relative value of AI standards. The document draws on successful and well-tested evaluation frameworks, tools, and metrics that are used for monitoring and assessing the effect of programmatic interventions in other domains to describe a possible approach. It begins by describing the context within which an evaluation would be designed, and then introduces a standard evaluation framework. These sections are followed by a description of what outputs and outcomes might result from the adoption and implementation of AI standards and the process whereby those AI standards are developed . Subsequent sections provide an overview of how the effectiveness of AI standards might be assessed and a conclusion.

One of the fundamental quests of AI is to produce agents that coordinate well with humans. This problem is challenging, especially in domains that lack high quality human behavioral data, because multi-agent reinforcement learning (RL) often converges to different equilibria from the ones that humans prefer. We propose a novel framework, instructRL, that enables humans to specify what kind of strategies they expect from their AI partners through natural language instructions. We use pretrained large language models to generate a prior policy conditioned on the human instruction and use the prior to regularize the RL objective. This leads to the RL agent converging to equilibria that are aligned with human preferences. We show that instructRL converges to human-like policies that satisfy the given instructions in a proof-of-concept environment as well as the challenging Hanabi benchmark. Finally, we show that knowing the language instruction significantly boosts human-AI coordination performance in human evaluations in Hanabi.

Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI models to access and interpret a user's private data (e.g., conversation history, user-AI interactions, app usage) to understand personal details such as biographical information, preferences, and social connections. However, due to the sensitive nature of such data, there are no publicly available datasets that allow us to assess an AI model's ability to understand users through direct access to personal information. To address this gap, we introduce a synthetic data generation pipeline that creates diverse, realistic user profiles and private documents simulating human activities. Leveraging this synthetic data, we present PersonaBench, a benchmark designed to evaluate AI models' performance in understanding personal information derived from simulated private user data. We evaluate Retrieval-Augmented Generation (RAG) pipelines using questions directly related to a user's personal information, supported by the relevant private documents provided to the models. Our results reveal that current retrieval-augmented AI models struggle to answer private questions by extracting personal information from user documents, highlighting the need for improved methodologies to enhance personalization capabilities in AI.

Explaining artificial intelligence (AI) predictions is increasingly important and even imperative in many high-stakes applications where humans are the ultimate decision-makers. In this work, we propose two novel architectures of self-interpretable image classifiers that first explain, and then predict (as opposed to post-hoc explanations) by harnessing the visual correspondences between a query image and exemplars. Our models consistently improve (by 1 to 4 points) on out-of-distribution (OOD) datasets while performing marginally worse (by 1 to 2 points) on in-distribution tests than ResNet-50 and a k-nearest neighbor classifier (kNN). Via a large-scale, human study on ImageNet and CUB, our correspondence-based explanations are found to be more useful to users than kNN explanations. Our explanations help users more accurately reject AI's wrong decisions than all other tested methods. Interestingly, for the first time, we show that it is possible to achieve complementary human-AI team accuracy (i.e., that is higher than either AI-alone or human-alone), in ImageNet and CUB image classification tasks.

Large language models (LLMs) are increasingly used in learning algorithms, evaluations, and optimization tasks. Recent studies have shown that using LLM-based optimizers to automatically optimize model prompts, demonstrations, predictions themselves, or other components can significantly enhance the performance of AI systems, as demonstrated by frameworks such as DSPy and TextGrad. However, optimizers built on language models themselves are usually designed by humans with manual design choices; optimizers themselves are not optimized. Moreover, these optimizers are general purpose by design, to be useful to a broad audience, and are not tailored for specific tasks. To address these challenges, we propose metaTextGrad, which focuses on designing a meta-optimizer to further enhance existing optimizers and align them to be good optimizers for a given task. Our approach consists of two key components: a meta prompt optimizer and a meta structure optimizer. The combination of these two significantly improves performance across multiple benchmarks, achieving an average absolute performance improvement of up to 6% compared to the best baseline.

As scaling laws in generative AI push performance, they also simultaneously concentrate the development of these models among actors with large computational resources. With a focus on text-to-image (T2I) generative models, we aim to address this bottleneck by demonstrating very low-cost training of large-scale T2I diffusion transformer models. As the computational cost of transformers increases with the number of patches in each image, we propose to randomly mask up to 75% of the image patches during training. We propose a deferred masking strategy that preprocesses all patches using a patch-mixer before masking, thus significantly reducing the performance degradation with masking, making it superior to model downscaling in reducing computational cost. We also incorporate the latest improvements in transformer architecture, such as the use of mixture-of-experts layers, to improve performance and further identify the critical benefit of using synthetic images in micro-budget training. Finally, using only 37M publicly available real and synthetic images, we train a 1.16 billion parameter sparse transformer with only \1,890 economical cost and achieve a 12.7 FID in zero-shot generation on the COCO dataset. Notably, our model achieves competitive FID and high-quality generations while incurring 118\times lower cost than stable diffusion models and 14\times lower cost than the current state-of-the-art approach that costs 28,400. We aim to release our end-to-end training pipeline to further democratize the training of large-scale diffusion models on micro-budgets.

Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world scenarios. While MuZero enables effective model learning for search in perfect information games, extending this paradigm to imperfect information games presents substantial challenges due to more nuanced look-ahead reasoning techniques and large number of states relevant for individual decisions. This paper introduces an algorithm LAMIR that learns an abstracted model of an imperfect information game directly from the agent-environment interaction. During test time, this trained model is used to perform look-ahead reasoning. The learned abstraction limits the size of each subgame to a manageable size, making theoretically principled look-ahead reasoning tractable even in games where previous methods could not scale. We empirically demonstrate that with sufficient capacity, LAMIR learns the exact underlying game structure, and with limited capacity, it still learns a valuable abstraction, which improves game playing performance of the pre-trained agents even in large games.

AMD GPUs offer state-of-the-art compute and memory bandwidth; however, peak performance AMD kernels are written in raw assembly. To address the difficulty of mapping AI algorithms to hardware, recent work proposes C++ embedded and PyTorch-inspired domain-specific languages like ThunderKittens (TK) to simplify high performance AI kernel development on NVIDIA hardware. We explore the extent to which such primitives -- for explicit tile-based programming with optimized memory accesses and fine-grained asynchronous execution across workers -- are NVIDIA-specific or general. We provide the first detailed study of the programming primitives that lead to performant AMD AI kernels, and we encapsulate these insights in the HipKittens (HK) programming framework. We find that tile-based abstractions used in prior DSLs generalize to AMD GPUs, however we need to rethink the algorithms that instantiate these abstractions for AMD. We validate the HK primitives across CDNA3 and CDNA4 AMD platforms. In evaluations, HK kernels compete with AMD's hand-optimized assembly kernels for GEMMs and attention, and consistently outperform compiler baselines. Moreover, assembly is difficult to scale to the breadth of AI workloads; reflecting this, in some settings HK outperforms all available kernel baselines by 1.2-2.4times (e.g., d=64 attention, GQA backwards, memory-bound kernels). These findings help pave the way for a single, tile-based software layer for high-performance AI kernels that translates across GPU vendors. HipKittens is released at: https://github.com/HazyResearch/HipKittens.

PanTS is a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis. It contains 36,390 CT scans from 145 medical centers, with expert-validated, voxel-wise annotations of over 993,000 anatomical structures, covering pancreatic tumors, pancreas head, body, and tail, and 24 surrounding anatomical structures such as vascular/skeletal structures and abdominal/thoracic organs. Each scan includes metadata such as patient age, sex, diagnosis, contrast phase, in-plane spacing, slice thickness, etc. AI models trained on PanTS achieve significantly better performance in pancreatic tumor detection, localization, and segmentation compared to those trained on existing public datasets. Our analysis indicates that these gains are directly attributable to the 16x larger-scale tumor annotations and indirectly supported by the 24 additional surrounding anatomical structures. As the largest and most comprehensive resource of its kind, PanTS offers a new benchmark for developing and evaluating AI models in pancreatic CT analysis.

Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications. Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these tools in their work. However, despite humans being the target end-users, most attribution methods were only evaluated on proxy automatic-evaluation metrics (Zhang et al. 2018; Zhou et al. 2016; Petsiuk et al. 2018). In this paper, we conduct the first user study to measure attribution map effectiveness in assisting humans in ImageNet classification and Stanford Dogs fine-grained classification, and when an image is natural or adversarial (i.e., contains adversarial perturbations). Overall, feature attribution is surprisingly not more effective than showing humans nearest training-set examples. On a harder task of fine-grained dog categorization, presenting attribution maps to humans does not help, but instead hurts the performance of human-AI teams compared to AI alone. Importantly, we found automatic attribution-map evaluation measures to correlate poorly with the actual human-AI team performance. Our findings encourage the community to rigorously test their methods on the downstream human-in-the-loop applications and to rethink the existing evaluation metrics.

Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better systems is the scarcity of benchmarks that capture the complexity of real therapeutic interactions. Most existing benchmarks either only test clinical knowledge through multiple-choice questions or assess single responses in isolation. To bridge this gap, we present MindEval, a framework designed in collaboration with Ph.D-level Licensed Clinical Psychologists for automatically evaluating language models in realistic, multi-turn mental health therapy conversations. Through patient simulation and automatic evaluation with LLMs, our framework balances resistance to gaming with reproducibility via its fully automated, model-agnostic design. We begin by quantitatively validating the realism of our simulated patients against human-generated text and by demonstrating strong correlations between automatic and human expert judgments. Then, we evaluate 12 state-of-the-art LLMs and show that all models struggle, scoring below 4 out of 6, on average, with particular weaknesses in problematic AI-specific patterns of communication. Notably, reasoning capabilities and model scale do not guarantee better performance, and systems deteriorate with longer interactions or when supporting patients with severe symptoms. We release all code, prompts, and human evaluation data.

OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability.OpenAI has claimed that the main techinique behinds o1 is the reinforcement learining. Recent works use alternative approaches like knowledge distillation to imitate o1's reasoning style, but their effectiveness is limited by the capability ceiling of the teacher model. Therefore, this paper analyzes the roadmap to achieving o1 from the perspective of reinforcement learning, focusing on four key components: policy initialization, reward design, search, and learning. Policy initialization enables models to develop human-like reasoning behaviors, equipping them with the ability to effectively explore solution spaces for complex problems. Reward design provides dense and effective signals via reward shaping or reward modeling, which is the guidance for both search and learning. Search plays a crucial role in generating high-quality solutions during both training and testing phases, which can produce better solutions with more computation. Learning utilizes the data generated by search for improving policy, which can achieve the better performance with more parameters and more searched data. Existing open-source projects that attempt to reproduce o1 can be seem as a part or a variant of our roadmap. Collectively, these components underscore how learning and search drive o1's advancement, making meaningful contributions to the development of LLM.

Resection and whole brain radiotherapy (WBRT) are the standards of care for the treatment of patients with brain metastases (BM) but are often associated with cognitive side effects. Stereotactic radiosurgery (SRS) involves a more targeted treatment approach and has been shown to avoid the side effects associated with WBRT. However, SRS requires precise identification and delineation of BM. While many AI algorithms have been developed for this purpose, their clinical adoption has been limited due to poor model performance in the clinical setting. Major reasons for non-generalizable algorithms are the limitations in the datasets used for training the AI network. The purpose of this study was to create a large, heterogenous, annotated BM dataset for training and validation of AI models to improve generalizability. We present a BM dataset of 200 patients with pretreatment T1, T1 post-contrast, T2, and FLAIR MR images. The dataset includes contrast-enhancing and necrotic 3D segmentations on T1 post-contrast and whole tumor (including peritumoral edema) 3D segmentations on FLAIR. Our dataset contains 975 contrast-enhancing lesions, many of which are sub centimeter, along with clinical and imaging feature information. We used a streamlined approach to database-building leveraging a PACS-integrated segmentation workflow.

Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) have significantly automated data science workflows, but a fundamental question persists: Can these agentic AI systems truly match the performance of human data scientists who routinely leverage domain-specific knowledge? We explore this question by designing a prediction task where a crucial latent variable is hidden in relevant image data instead of tabular features. As a result, agentic AI that generates generic codes for modeling tabular data cannot perform well, while human experts could identify the important hidden variable using domain knowledge. We demonstrate this idea with a synthetic dataset for property insurance. Our experiments show that agentic AI that relies on generic analytics workflow falls short of methods that use domain-specific insights. This highlights a key limitation of the current agentic AI for data science and underscores the need for future research to develop agentic AI systems that can better recognize and incorporate domain knowledge.

The current literature on AI-advised decision making -- involving explainable AI systems advising human decision makers -- presents a series of inconclusive and confounding results. To synthesize these findings, we propose a simple theory that elucidates the frequent failure of AI explanations to engender appropriate reliance and complementary decision making performance. We argue explanations are only useful to the extent that they allow a human decision maker to verify the correctness of an AI's prediction, in contrast to other desiderata, e.g., interpretability or spelling out the AI's reasoning process. Prior studies find in many decision making contexts AI explanations do not facilitate such verification. Moreover, most tasks fundamentally do not allow easy verification, regardless of explanation method, limiting the potential benefit of any type of explanation. We also compare the objective of complementary performance with that of appropriate reliance, decomposing the latter into the notions of outcome-graded and strategy-graded reliance.

The performance of AI-based software vulnerability detection systems is often limited by their poor generalization to unknown codebases. In this research, we explore the impact of data quality and model architecture on the generalizability of vulnerability detection systems. By generalization we mean ability of high vulnerability detection performance across different C/C++ software projects not seen during training. Through a series of experiments, we demonstrate that improvements in dataset diversity and quality substantially enhance detection performance. Additionally, we compare multiple encoder-only and decoder-only models, finding that encoder based models outperform in terms of accuracy and generalization. Our model achieves 6.8% improvement in recall on the benchmark BigVul[1] dataset, also outperforming on unseen projects, hence showing enhanced generalizability. These results highlight the role of data quality and model selection in the development of robust vulnerability detection systems. Our findings suggest a direction for future systems having high cross-project effectiveness.

In this report, we pose the following question: Who is the most intelligent AI model to date, as measured by the OlympicArena (an Olympic-level, multi-discipline, multi-modal benchmark for superintelligent AI)? We specifically focus on the most recently released models: Claude-3.5-Sonnet, Gemini-1.5-Pro, and GPT-4o. For the first time, we propose using an Olympic medal Table approach to rank AI models based on their comprehensive performance across various disciplines. Empirical results reveal: (1) Claude-3.5-Sonnet shows highly competitive overall performance over GPT-4o, even surpassing GPT-4o on a few subjects (i.e., Physics, Chemistry, and Biology). (2) Gemini-1.5-Pro and GPT-4V are ranked consecutively just behind GPT-4o and Claude-3.5-Sonnet, but with a clear performance gap between them. (3) The performance of AI models from the open-source community significantly lags behind these proprietary models. (4) The performance of these models on this benchmark has been less than satisfactory, indicating that we still have a long way to go before achieving superintelligence. We remain committed to continuously tracking and evaluating the performance of the latest powerful models on this benchmark (available at https://github.com/GAIR-NLP/OlympicArena).

AI research agents offer the promise to accelerate scientific progress by automating the design, implementation, and training of machine learning models. However, the field is still in its infancy, and the key factors driving the success or failure of agent trajectories are not fully understood. We examine the role that ideation diversity plays in agent performance. First, we analyse agent trajectories on MLE-bench, a well-known benchmark to evaluate AI research agents, across different models and agent scaffolds. Our analysis reveals that different models and agent scaffolds yield varying degrees of ideation diversity, and that higher-performing agents tend to have increased ideation diversity. Further, we run a controlled experiment where we modify the degree of ideation diversity, demonstrating that higher ideation diversity results in stronger performance. Finally, we strengthen our results by examining additional evaluation metrics beyond the standard medal-based scoring of MLE-bench, showing that our findings still hold across other agent performance metrics.

This study compares the performance of AI-generated and human-written product descriptions using a multifaceted evaluation model. We analyze descriptions for 100 products generated by four AI models (Gemma 2B, LLAMA, GPT2, and ChatGPT 4) with and without sample descriptions, against human-written descriptions. Our evaluation metrics include sentiment, readability, persuasiveness, Search Engine Optimization(SEO), clarity, emotional appeal, and call-to-action effectiveness. The results indicate that ChatGPT 4 performs the best. In contrast, other models demonstrate significant shortcomings, producing incoherent and illogical output that lacks logical structure and contextual relevance. These models struggle to maintain focus on the product being described, resulting in disjointed sentences that do not convey meaningful information. This research provides insights into the current capabilities and limitations of AI in the creation of content for e-Commerce.

With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by systematically introducing the mechanisms of human long-term memory, then explores AI long-term memory mechanisms, establishing a mapping between the two. Based on the mapping relationships identified, we extend the current cognitive architectures and propose the Cognitive Architecture of Self-Adaptive Long-term Memory (SALM). SALM provides a theoretical framework for the practice of AI long-term memory and holds potential for guiding the creation of next-generation long-term memory driven AI systems. Finally, we delve into the future directions and application prospects of AI long-term memory.

The PI-CAI (Prostate Imaging: Cancer AI) challenge led to expert-level diagnostic algorithms for clinically significant prostate cancer detection. The algorithms receive biparametric MRI scans as input, which consist of T2-weighted and diffusion-weighted scans. These scans can be misaligned due to multiple factors in the scanning process. Image registration can alleviate this issue by predicting the deformation between the sequences. We investigate the effect of image registration on the diagnostic performance of AI-based prostate cancer diagnosis. First, the image registration algorithm, developed in MeVisLab, is analyzed using a dataset with paired lesion annotations. Second, the effect on diagnosis is evaluated by comparing case-level cancer diagnosis performance between using the original dataset, rigidly aligned diffusion-weighted scans, or deformably aligned diffusion-weighted scans. Rigid registration showed no improvement. Deformable registration demonstrated a substantial improvement in lesion overlap (+10% median Dice score) and a positive yet non-significant improvement in diagnostic performance (+0.3% AUROC, p=0.18). Our investigation shows that a substantial improvement in lesion alignment does not directly lead to a significant improvement in diagnostic performance. Qualitative analysis indicated that jointly developing image registration methods and diagnostic AI algorithms could enhance diagnostic accuracy and patient outcomes.

The advancement of large language models (LLMs) has made it difficult to differentiate human-written text from AI-generated text. Several AI-text detectors have been developed in response, which typically utilize a fixed global threshold (e.g., {\theta} = 0.5) to classify machine-generated text. However, we find that one universal threshold can fail to account for subgroup-specific distributional variations. For example, when using a fixed threshold, detectors make more false positive errors on shorter human-written text than longer, and more positive classifications on neurotic writing styles than open among long text. These discrepancies can lead to misclassification that disproportionately affects certain groups. We address this critical limitation by introducing FairOPT, an algorithm for group-specific threshold optimization in AI-generated content classifiers. Our approach partitions data into subgroups based on attributes (e.g., text length and writing style) and learns decision thresholds for each group, which enables careful balancing of performance and fairness metrics within each subgroup. In experiments with four AI text classifiers on three datasets, FairOPT enhances overall F1 score and decreases balanced error rate (BER) discrepancy across subgroups. Our framework paves the way for more robust and fair classification criteria in AI-generated output detection.

LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness, overlooking the diversity of methods behind solutions. True innovation depends not only on producing correct answers but also on the originality of the approach. We present InnoGym, the first benchmark and framework designed to systematically evaluate the innovation potential of AI agents. InnoGym introduces two complementary metrics: performance gain, which measures improvement over the best-known solutions, and novelty, which captures methodological differences from prior approaches. The benchmark includes 18 carefully curated tasks from real-world engineering and scientific domains, each standardized through resource filtering, evaluator validation, and solution collection. In addition, we provide iGym, a unified execution environment for reproducible and long-horizon evaluations. Extensive experiments show that while some agents produce novel approaches, their lack of robustness limits performance gains. These results highlight a key gap between creativity and effectiveness, underscoring the need for benchmarks that evaluate both.

The emergence of Large Language Models (LLMs) have fundamentally altered the way we interact with digital systems and have led to the pursuit of LLM powered AI agents to assist in daily workflows. LLMs, whilst powerful and capable of demonstrating some emergent properties, are not logical reasoners and often struggle to perform well at all sub-tasks carried out by an AI agent to plan and execute a workflow. While existing studies tackle this lack of proficiency by generalised pretraining at a huge scale or by specialised fine-tuning for tool use, we assess if a system comprising of a coalition of pretrained LLMs, each exhibiting specialised performance at individual sub-tasks, can match the performance of single model agents. The coalition of models approach showcases its potential for building robustness and reducing the operational costs of these AI agents by leveraging traits exhibited by specific models. Our findings demonstrate that fine-tuning can be mitigated by considering a coalition of pretrained models and believe that this approach can be applied to other non-agentic systems which utilise LLMs.

Despite significant advancements in image segmentation and object detection, understanding complex scenes remains a significant challenge. Here, we focus on graphical humor as a paradigmatic example of image interpretation that requires elucidating the interaction of different scene elements in the context of prior cognitive knowledge. This paper introduces HumorDB, a novel, controlled, and carefully curated dataset designed to evaluate and advance visual humor understanding by AI systems. The dataset comprises diverse images spanning photos, cartoons, sketches, and AI-generated content, including minimally contrastive pairs where subtle edits differentiate between humorous and non-humorous versions. We evaluate humans, state-of-the-art vision models, and large vision-language models on three tasks: binary humor classification, funniness rating prediction, and pairwise humor comparison. The results reveal a gap between current AI systems and human-level humor understanding. While pretrained vision-language models perform better than vision-only models, they still struggle with abstract sketches and subtle humor cues. Analysis of attention maps shows that even when models correctly classify humorous images, they often fail to focus on the precise regions that make the image funny. Preliminary mechanistic interpretability studies and evaluation of model explanations provide initial insights into how different architectures process humor. Our results identify promising trends and current limitations, suggesting that an effective understanding of visual humor requires sophisticated architectures capable of detecting subtle contextual features and bridging the gap between visual perception and abstract reasoning. All the code and data are available here: https://github.com/kreimanlab/HumorDB{https://github.com/kreimanlab/HumorDB}

Diabetic retinopathy (DR) is a leading cause of vision loss in working-age adults. While screening reduces the risk of blindness, traditional imaging is often costly and inaccessible. Artificial intelligence (AI) algorithms present a scalable diagnostic solution, but concerns regarding fairness and generalization persist. This work evaluates the fairness and performance of image-trained models in DR prediction, as well as the impact of disentanglement as a bias mitigation technique, using the diverse mBRSET fundus dataset. Three models, ConvNeXt V2, DINOv2, and Swin V2, were trained on macula images to predict DR and sensitive attributes (SAs) (e.g., age and gender/sex). Fairness was assessed between subgroups of SAs, and disentanglement was applied to reduce bias. All models achieved high DR prediction performance in diagnosing (up to 94% AUROC) and could reasonably predict age and gender/sex (91% and 77% AUROC, respectively). Fairness assessment suggests disparities, such as a 10% AUROC gap between age groups in DINOv2. Disentangling SAs from DR prediction had varying results, depending on the model selected. Disentanglement improved DINOv2 performance (2% AUROC gain), but led to performance drops in ConvNeXt V2 and Swin V2 (7% and 3%, respectively). These findings highlight the complexity of disentangling fine-grained features in fundus imaging and emphasize the importance of fairness in medical imaging AI to ensure equitable and reliable healthcare solutions.

Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL), are language models (LMs) fine-tuned on large conversational datasets. Training these models is expensive, both in terms of computational resources and time, and it is hard to keep them up to date with new conversational skills. A simple yet unexplored solution is prompt-based few-shot learning (Brown et al. 2020) which does not require gradient-based fine-tuning but instead uses a few examples in the LM context as the only source of learning. In this paper, we explore prompt-based few-shot learning in dialogue tasks. We benchmark LMs of different sizes in nine response generation tasks, which include four knowledge-grounded tasks, a task-oriented generations task, three open-chat tasks, and controlled stylistic generation, and five conversational parsing tasks, which include dialogue state tracking, graph path generation, persona information extraction, document retrieval, and internet query generation. The current largest released LM (GPT-J-6B) using prompt-based few-shot learning, and thus requiring no training, achieves competitive performance to fully trained state-of-the-art models. Moreover, we propose a novel prompt-based few-shot classifier, that also does not require any fine-tuning, to select the most appropriate prompt given a dialogue history. Finally, by combining the power of prompt-based few-shot learning and a Skill Selector, we create an end-to-end chatbot named the Few-Shot Bot (FSB), which automatically selects the most appropriate conversational skill, queries different knowledge bases or the internet, and uses the retrieved knowledge to generate a human-like response, all using only few dialogue examples per skill.

Natural-language prompts have recently been used to coax pretrained language models into performing other AI tasks, using a fill-in-the-blank paradigm (Petroni et al., 2019) or a few-shot extrapolation paradigm (Brown et al., 2020). For example, language models retain factual knowledge from their training corpora that can be extracted by asking them to "fill in the blank" in a sentential prompt. However, where does this prompt come from? We explore the idea of learning prompts by gradient descent -- either fine-tuning prompts taken from previous work, or starting from random initialization. Our prompts consist of "soft words," i.e., continuous vectors that are not necessarily word type embeddings from the language model. Furthermore, for each task, we optimize a mixture of prompts, learning which prompts are most effective and how to ensemble them. Across multiple English LMs and tasks, our approach hugely outperforms previous methods, showing that the implicit factual knowledge in language models was previously underestimated. Moreover, this knowledge is cheap to elicit: random initialization is nearly as good as informed initialization.

The advent of automation in particular Software Engineering (SE) tasks has transitioned from theory to reality. Numerous scholarly articles have documented the successful application of Artificial Intelligence to address issues in areas such as project management, modeling, testing, and development. A recent innovation is the introduction of ChatGPT, an ML-infused chatbot, touted as a resource proficient in generating programming codes and formulating software testing strategies for developers and testers respectively. Although there is speculation that AI-based computation can increase productivity and even substitute software engineers in software development, there is currently a lack of empirical evidence to verify this. Moreover, despite the primary focus on enhancing the accuracy of AI systems, non-functional requirements including energy efficiency, vulnerability, fairness (i.e., human bias), and safety frequently receive insufficient attention. This paper posits that a comprehensive comparison of software engineers and AI-based solutions, considering various evaluation criteria, is pivotal in fostering human-machine collaboration, enhancing the reliability of AI-based methods, and understanding task suitability for humans or AI. Furthermore, it facilitates the effective implementation of cooperative work structures and human-in-the-loop processes. This paper conducts an empirical investigation, contrasting the performance of software engineers and AI systems, like ChatGPT, across different evaluation metrics. The empirical study includes a case of assessing ChatGPT-generated code versus code produced by developers and uploaded in Leetcode.

Molecule pretraining has quickly become the go-to schema to boost the performance of AI-based drug discovery. Naturally, molecules can be represented as 2D topological graphs or 3D geometric point clouds. Although most existing pertaining methods focus on merely the single modality, recent research has shown that maximizing the mutual information (MI) between such two modalities enhances the molecule representation ability. Meanwhile, existing molecule multi-modal pretraining approaches approximate MI based on the representation space encoded from the topology and geometry, thus resulting in the loss of critical structural information of molecules. To address this issue, we propose MoleculeSDE. MoleculeSDE leverages group symmetric (e.g., SE(3)-equivariant and reflection-antisymmetric) stochastic differential equation models to generate the 3D geometries from 2D topologies, and vice versa, directly in the input space. It not only obtains tighter MI bound but also enables prosperous downstream tasks than the previous work. By comparing with 17 pretraining baselines, we empirically verify that MoleculeSDE can learn an expressive representation with state-of-the-art performance on 26 out of 32 downstream tasks.

Early tumor detection save lives. Each year, more than 300 million computed tomography (CT) scans are performed worldwide, offering a vast opportunity for effective cancer screening. However, detecting small or early-stage tumors on these CT scans remains challenging, even for experts. Artificial intelligence (AI) models can assist by highlighting suspicious regions, but training such models typically requires extensive tumor masks--detailed, voxel-wise outlines of tumors manually drawn by radiologists. Drawing these masks is costly, requiring years of effort and millions of dollars. In contrast, nearly every CT scan in clinical practice is already accompanied by medical reports describing the tumor's size, number, appearance, and sometimes, pathology results--information that is rich, abundant, and often underutilized for AI training. We introduce R-Super, which trains AI to segment tumors that match their descriptions in medical reports. This approach scales AI training with large collections of readily available medical reports, substantially reducing the need for manually drawn tumor masks. When trained on 101,654 reports, AI models achieved performance comparable to those trained on 723 masks. Combining reports and masks further improved sensitivity by +13% and specificity by +8%, surpassing radiologists in detecting five of the seven tumor types. Notably, R-Super enabled segmentation of tumors in the spleen, gallbladder, prostate, bladder, uterus, and esophagus, for which no public masks or AI models previously existed. This study challenges the long-held belief that large-scale, labor-intensive tumor mask creation is indispensable, establishing a scalable and accessible path toward early detection across diverse tumor types. We plan to release our trained models, code, and dataset at https://github.com/MrGiovanni/R-Super

We explore the AI2050 "hard problems" that block the promise of AI and cause AI risks: (1) developing general capabilities of the systems; (2) assuring the performance of AI systems and their training processes; (3) aligning system goals with human goals; (4) enabling great applications of AI in real life; (5) addressing economic disruptions; (6) ensuring the participation of all; (7) at the same time ensuring socially responsible deployment; (8) addressing any geopolitical disruptions that AI causes; (9) promoting sound governance of the technology; and (10) managing the philosophical disruptions for humans living in the age of AI. For each problem, we outline the area, identify significant recent work, and suggest ways forward. [Note: this paper reviews literature through January 2023.]

AI-driven medical history-taking is an important component in symptom checking, automated patient intake, triage, and other AI virtual care applications. As history-taking is extremely varied, machine learning models require a significant amount of data to train. To overcome this challenge, existing systems are developed using indirect data or expert knowledge. This leads to a training-inference gap as models are trained on different kinds of data than what they observe at inference time. In this work, we present a two-stage re-ranking approach that helps close the training-inference gap by re-ranking the first-stage question candidates using a dialogue-contextualized model. For this, we propose a new model, global re-ranker, which cross-encodes the dialogue with all questions simultaneously, and compare it with several existing neural baselines. We test both transformer and S4-based language model backbones. We find that relative to the expert system, the best performance is achieved by our proposed global re-ranker with a transformer backbone, resulting in a 30% higher normalized discount cumulative gain (nDCG) and a 77% higher mean average precision (mAP).

We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.

Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we investigate the capabilities of Large Language Models (LLMs) for reinforcement learning (RL) across a diversity of interactive domains. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly, by first generating reward models to train an agent with RL. Our results show that, even without task-specific fine-tuning, LLMs excel at reward modeling. In particular, crafting rewards through artificial intelligence (AI) feedback yields the most generally applicable approach and can enhance performance by improving credit assignment and exploration. Finally, in environments with unfamiliar dynamics, we explore how fine-tuning LLMs with synthetic data can significantly improve their reward modeling capabilities while mitigating catastrophic forgetting, further broadening their utility in sequential decision-making tasks.

This paper introduces ArtELingo, a new benchmark and dataset, designed to encourage work on diversity across languages and cultures. Following ArtEmis, a collection of 80k artworks from WikiArt with 0.45M emotion labels and English-only captions, ArtELingo adds another 0.79M annotations in Arabic and Chinese, plus 4.8K in Spanish to evaluate "cultural-transfer" performance. More than 51K artworks have 5 annotations or more in 3 languages. This diversity makes it possible to study similarities and differences across languages and cultures. Further, we investigate captioning tasks, and find diversity improves the performance of baseline models. ArtELingo is publicly available at https://www.artelingo.org/ with standard splits and baseline models. We hope our work will help ease future research on multilinguality and culturally-aware AI.

As centralized AI hits compute ceilings and diminishing returns from ever-larger training runs, meeting demand requires an inference layer that scales horizontally in both capacity and capability. We present Fortytwo, a novel protocol that leverages swarm intelligence principles and distributed pairwise ranking consensus to achieve superior performance in AI inference. Our approach reimagines collaboration among AI nodes using swarm inference: a peer-ranked, reputation-weighted consensus across heterogeneous models that surfaces the highest-quality responses. Using pairwise ranking with a custom Bradley-Terry-style aggregation model, we demonstrate that swarm inference substantially outperforms majority voting, achieving 85.90% on GPQA Diamond versus 68.69% for majority voting with the same model set - an improvement of +17.21 percentage points (approximately +25.1% relative). The protocol incorporates on-chain reputation so node influence adapts to demonstrated accuracy over time, yielding a meritocratic consensus that filters low-quality or malicious participants. To resist Sybil attacks, Fortytwo employs proof-of-capability in its consensus: nodes must successfully complete calibration/test requests and stake reputation to enter ranking rounds, making multi-identity attacks economically unattractive while preserving openness. Across six challenging benchmarks, including GPQA Diamond, LiveCodeBench, and AIME, our evaluation indicates higher accuracy and strong resilience to adversarial and noisy free-form prompting (e.g., prompt-injection degradation of only 0.12% versus 6.20% for a monolithic single-model baseline), while retaining practical deployability. Together, these results establish a foundation for decentralized AI systems - democratizing access to high-quality inference through collective intelligence without sacrificing reliability or security.

AI democratization aims to create a world in which the average person can utilize AI techniques. To achieve this goal, numerous research institutes have attempted to make their results accessible to the public. In particular, large pre-trained models trained on large-scale data have shown unprecedented potential, and their release has had a significant impact. However, most of the released models specialize in the English language, and thus, AI democratization in non-English-speaking communities is lagging significantly. To reduce this gap in AI access, we released Generative Pre-trained Transformer (GPT), Contrastive Language and Image Pre-training (CLIP), Stable Diffusion, and Hidden-unit Bidirectional Encoder Representations from Transformers (HuBERT) pre-trained in Japanese. By providing these models, users can freely interface with AI that aligns with Japanese cultural values and ensures the identity of Japanese culture, thus enhancing the democratization of AI. Additionally, experiments showed that pre-trained models specialized for Japanese can efficiently achieve high performance in Japanese tasks.

We introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embedding models that require massive contrastive pretraining, sophisticated training pipelines, and costly synthetic training data, F2LLM is directly finetuned from foundation models on 6 million query-document-negative tuples curated from open-source, non-synthetic datasets, striking a strong balance between training cost, model size, and embedding performance. On the MTEB English leaderboard, F2LLM-4B ranks 2nd among models with approximately 4B parameters and 7th overall, while F2LLM-1.7B ranks 1st among models in the 1B-2B size range. To facilitate future research in the field, we release the models, training dataset, and code, positioning F2LLM as a strong, reproducible, and budget-friendly baseline for future works.

Artificial intelligence (AI) methods have become critical in scientific applications to help accelerate scientific discovery. Large language models (LLMs) are being considered as a promising approach to address some of the challenging problems because of their superior generalization capabilities across domains. The effectiveness of the models and the accuracy of the applications is contingent upon their efficient execution on the underlying hardware infrastructure. Specialized AI accelerator hardware systems have recently become available for accelerating AI applications. However, the comparative performance of these AI accelerators on large language models has not been previously studied. In this paper, we systematically study LLMs on multiple AI accelerators and GPUs and evaluate their performance characteristics for these models. We evaluate these systems with (i) a micro-benchmark using a core transformer block, (ii) a GPT- 2 model, and (iii) an LLM-driven science use case, GenSLM. We present our findings and analyses of the models' performance to better understand the intrinsic capabilities of AI accelerators. Furthermore, our analysis takes into account key factors such as sequence lengths, scaling behavior, sparsity, and sensitivity to gradient accumulation steps.

Background: AI-based classification models are essential for improving lung cancer diagnosis. However, the relative performance of lesion-level versus chest-region models in internal and external datasets remains unclear. Purpose: This study evaluates the performance of lesion-level and chest-region models for lung cancer classification, comparing their effectiveness across internal Duke Lung Nodule Dataset 2024 (DLND24) and external (LUNA16, NLST) datasets, with a focus on subgroup analyses by demographics, histology, and imaging characteristics. Materials and Methods: Two AI models were trained: one using lesion-centric patches (64,64,64) and the other using chest-region patches (512,512,8). Internal validation was conducted on DLND24, while external validation utilized LUNA16 and NLST datasets. The models performances were assessed using AUC-ROC, with subgroup analyses for demographic, clinical, and imaging factors. Statistical comparisons were performed using DeLongs test. Gradient-based visualizations and probability distribution were further used for analysis. Results: The lesion-level model consistently outperformed the chest-region model across datasets. In internal validation, the lesion-level model achieved an AUC of 0.71(CI: 0.61-0.81), compared to 0.68(0.57-0.77) for the chest-region model. External validation showed similar trends, with AUCs of 0.90(0.87-0.92) and 0.81(0.79-0.82) on LUNA16 and NLST, respectively. Subgroup analyses revealed significant advantages for lesion-level models in certain histological subtypes (adenocarcinoma) and imaging conditions (CT manufacturers). Conclusion: Lesion-level models demonstrate superior classification performance, especially for external datasets and challenging subgroups, suggesting their clinical utility for precision lung cancer diagnostics.

Recent work has proposed artificial intelligence (AI) models that can learn to decide whether to make a prediction for an instance of a task or to delegate it to a human by considering both parties' capabilities. In simulations with synthetically generated or context-independent human predictions, delegation can help improve the performance of human-AI teams -- compared to humans or the AI model completing the task alone. However, so far, it remains unclear how humans perform and how they perceive the task when they are aware that an AI model delegated task instances to them. In an experimental study with 196 participants, we show that task performance and task satisfaction improve through AI delegation, regardless of whether humans are aware of the delegation. Additionally, we identify humans' increased levels of self-efficacy as the underlying mechanism for these improvements in performance and satisfaction. Our findings provide initial evidence that allowing AI models to take over more management responsibilities can be an effective form of human-AI collaboration in workplaces.

The rapid growth of deep learning has driven exponential increases in model parameters and computational demands. NVIDIA GPUs and their CUDA-based software ecosystem provide robust support for parallel computing, significantly alleviating computational bottlenecks. Meanwhile, due to the cultivation of user programming habits and the high performance of GPUs, the CUDA ecosystem has established a dominant position in the field of parallel software. This dominance requires other hardware platforms to support CUDA-based software with performance portability. However, translating CUDA code to other platforms poses significant challenges due to differences in parallel programming paradigms and hardware architectures. Existing approaches rely on language extensions, domain-specific languages (DSLs), or compilers but face limitations in workload coverage and generalizability. Moreover, these methods often incur substantial development costs. Recently, LLMs have demonstrated extraordinary potential in various vertical domains, especially in code-related tasks. However, the performance of existing LLMs in CUDA transpilation, particularly for high-performance code, remains suboptimal. To address these challenges, we propose a novel framework for generating high-performance CUDA and corresponding platform code pairs, leveraging AI compiler and automatic optimization technology. We further enhance the framework with a graph-based data augmentation method and introduce HPCTransEval, a benchmark for evaluating LLM performance on CUDA transpilation. We conduct experiments using CUDA-to-CPU transpilation as a case study on leading LLMs. The speedup ratio of the CPU operators has an average improvemnet of 43.8\%, highlighting the potential of LLMs to address compatibility challenges within the CUDA ecosystem. Our code is available at https://github.com/PJLAB-CHIP/HPCTransCompile.

Understanding player shooting profiles is an essential part of basketball analysis: knowing where certain opposing players like to shoot from can help coaches neutralize offensive gameplans from their opponents; understanding where their players are most comfortable can lead them to developing more effective offensive strategies. An automatic tool that can provide these performance profiles in a timely manner can become invaluable for coaches to maximize both the effectiveness of their game plan as well as the time dedicated to practice and other related activities. Additionally, basketball is dictated by many variables, such as playstyle and game dynamics, that can change the flow of the game and, by extension, player performance profiles. It is crucial that the performance profiles can reflect the diverse playstyles, as well as the fast-changing dynamics of the game. We present a tool that can visualize player performance profiles in a timely manner while taking into account factors such as play-style and game dynamics. Our approach generates interpretable heatmaps that allow us to identify and analyze how non-spatial factors, such as game dynamics or playstyle, affect player performance profiles.

Achieving robust performance and fairness across diverse patient populations remains a challenge in developing clinically deployable deep learning models for diagnostic imaging. Synthetic data generation has emerged as a promising strategy to address limitations in dataset scale and diversity. We introduce RoentGen-v2, a text-to-image diffusion model for chest radiographs that enables fine-grained control over both radiographic findings and patient demographic attributes, including sex, age, and race/ethnicity. RoentGen-v2 is the first model to generate clinically plausible images with demographic conditioning, facilitating the creation of a large, demographically balanced synthetic dataset comprising over 565,000 images. We use this large synthetic dataset to evaluate optimal training pipelines for downstream disease classification models. In contrast to prior work that combines real and synthetic data naively, we propose an improved training strategy that leverages synthetic data for supervised pretraining, followed by fine-tuning on real data. Through extensive evaluation on over 137,000 chest radiographs from five institutions, we demonstrate that synthetic pretraining consistently improves model performance, generalization to out-of-distribution settings, and fairness across demographic subgroups. Across datasets, synthetic pretraining led to a 6.5% accuracy increase in the performance of downstream classification models, compared to a modest 2.7% increase when naively combining real and synthetic data. We observe this performance improvement simultaneously with the reduction of the underdiagnosis fairness gap by 19.3%. These results highlight the potential of synthetic imaging to advance equitable and generalizable medical deep learning under real-world data constraints. We open source our code, trained models, and synthetic dataset at https://github.com/StanfordMIMI/RoentGen-v2 .

This study investigates the metacognitive capabilities of Large Language Models relative to human metacognition in the context of the International Coaching Federation ICF mimicking exam, a situational judgment test related to coaching competencies. Using a mixed method approach, we assessed the metacognitive performance, including sensitivity, accuracy in probabilistic predictions, and bias, of human participants and five advanced LLMs (GPT-4, Claude-3-Opus 3, Mistral Large, Llama 3, and Gemini 1.5 Pro). The results indicate that LLMs outperformed humans across all metacognitive metrics, particularly in terms of reduced overconfidence, compared to humans. However, both LLMs and humans showed less adaptability in ambiguous scenarios, adhering closely to predefined decision frameworks. The study suggests that Generative AI can effectively engage in human-like metacognitive processing without conscious awareness. Implications of the study are discussed in relation to development of AI simulators that scaffold cognitive and metacognitive aspects of mastering coaching competencies. More broadly, implications of these results are discussed in relation to development of metacognitive modules that lead towards more autonomous and intuitive AI systems.

Geospatial Foundation Models (GeoFMs) are transforming Earth Observation (EO), but evaluation lacks standardized protocols. GEO-Bench-2 addresses this with a comprehensive framework spanning classification, segmentation, regression, object detection, and instance segmentation across 19 permissively-licensed datasets. We introduce ''capability'' groups to rank models on datasets that share common characteristics (e.g., resolution, bands, temporality). This enables users to identify which models excel in each capability and determine which areas need improvement in future work. To support both fair comparison and methodological innovation, we define a prescriptive yet flexible evaluation protocol. This not only ensures consistency in benchmarking but also facilitates research into model adaptation strategies, a key and open challenge in advancing GeoFMs for downstream tasks. Our experiments show that no single model dominates across all tasks, confirming the specificity of the choices made during architecture design and pretraining. While models pretrained on natural images (ConvNext ImageNet, DINO V3) excel on high-resolution tasks, EO-specific models (TerraMind, Prithvi, and Clay) outperform them on multispectral applications such as agriculture and disaster response. These findings demonstrate that optimal model choice depends on task requirements, data modalities, and constraints. This shows that the goal of a single GeoFM model that performs well across all tasks remains open for future research. GEO-Bench-2 enables informed, reproducible GeoFM evaluation tailored to specific use cases. Code, data, and leaderboard for GEO-Bench-2 are publicly released under a permissive license.

During the COVID-19 pandemic, a significant effort has gone into developing ML-driven epidemic forecasting techniques. However, benchmarks do not exist to claim if a new AI/ML technique is better than the existing ones. The "covid-forecast-hub" is a collection of more than 30 teams, including us, that submit their forecasts weekly to the CDC. It is not possible to declare whether one method is better than the other using those forecasts because each team's submission may correspond to different techniques over the period and involve human interventions as the teams are continuously changing/tuning their approach. Such forecasts may be considered "human-expert" forecasts and do not qualify as AI/ML approaches, although they can be used as an indicator of human expert performance. We are interested in supporting AI/ML research in epidemic forecasting which can lead to scalable forecasting without human intervention. Which modeling technique, learning strategy, and data pre-processing technique work well for epidemic forecasting is still an open problem. To help advance the state-of-the-art AI/ML applied to epidemiology, a benchmark with a collection of performance points is needed and the current "state-of-the-art" techniques need to be identified. We propose EpiBench a platform consisting of community-driven benchmarks for AI/ML applied to epidemic forecasting to standardize the challenge with a uniform evaluation protocol. In this paper, we introduce a prototype of EpiBench which is currently running and accepting submissions for the task of forecasting COVID-19 cases and deaths in the US states and We demonstrate that we can utilize the prototype to develop an ensemble relying on fully automated epidemic forecasts (no human intervention) that reaches human-expert level ensemble currently being used by the CDC.

Modern natural language processing models have achieved unprecedented scale, yet the tools for their evaluation often remain a computational bottleneck, limiting the pace of research. This is particularly acute for in-training evaluation metrics, such as per-sentence reward signals in Reinforcement Learning, which must operate efficiently on batches of token IDs directly on the GPU. In this paper, we introduce TensorBLEU, a novel implementation of the BLEU metric designed from the ground up for this specific use case. Our approach is fully vectorized for GPU-accelerated, per-sentence computation within PyTorch and introduces a memory-efficient counting mechanism. By creating a compact, batch-specific dictionary of n-grams using torch.unique, our method avoids the prohibitive memory costs of traditional hashing-based vectorization, making it practical for large-vocabulary models. We benchmark TensorBLEU against NLTK, the standard library for token-ID-based BLEU calculation on the CPU. Experiments show that TensorBLEU provides speedups of over 13x on consumer-grade GPUs (NVIDIA T4) and exceeding 40x on data-center-class hardware (NVIDIA A100). This performance transforms a significant bottleneck into a negligible part of the training loop. By clearly defining its role as a "Token-ID BLEU" for development purposes and open-sourcing our implementation, we provide a powerful tool for accelerating research in areas like RL-based model fine-tuning.

While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge. Indeed, truthfulness requires more than accuracy -- models must also recognize uncertainty and abstain when unsure to avoid hallucinations. This presents a fundamental challenge for existing methods: approaches that optimize for accuracy often amplify hallucinations, while those that encourage abstention can become overly conservative, sacrificing correct answers. Both extremes ultimately compromise truthfulness. In this work, we present TruthRL, a general reinforcement learning (RL) framework that directly optimizes the truthfulness of LLMs. Specifically, we implement TruthRL using GRPO with a simple yet effective ternary reward that distinguishes correct answers, hallucinations, and abstentions. It incentivizes models to reduce hallucinations not only by providing correct responses, but also by enabling abstention when uncertain, thereby improving truthfulness. Extensive experiments across four knowledge-intensive benchmarks show that, compared to vanilla RL, TruthRL significantly reduces hallucinations by 28.9% and improves truthfulness by 21.1%, with consistent gains across various backbone models (e.g., Qwen, Llama) under both retrieval and non-retrieval setups. In-depth ablation study demonstrates that vanilla accuracy-driven methods, such as supervised fine-tuning or RL with a binary reward, struggle to balance factual correctness and uncertainty. In contrast, our proposed truthfulness-driven TruthRL achieves strong performance in both accuracy and truthfulness, underscoring the importance of learning objective design for developing truthful LLMs.

Self-supervised learning holds the promise of eliminating the need for manual data annotation, enabling models to scale effortlessly to massive datasets and larger architectures. By not being tailored to specific tasks or domains, this training paradigm has the potential to learn visual representations from diverse sources, ranging from natural to aerial images -- using a single algorithm. This technical report introduces DINOv3, a major milestone toward realizing this vision by leveraging simple yet effective strategies. First, we leverage the benefit of scaling both dataset and model size by careful data preparation, design, and optimization. Second, we introduce a new method called Gram anchoring, which effectively addresses the known yet unsolved issue of dense feature maps degrading during long training schedules. Finally, we apply post-hoc strategies that further enhance our models' flexibility with respect to resolution, model size, and alignment with text. As a result, we present a versatile vision foundation model that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. We also share the DINOv3 suite of vision models, designed to advance the state of the art on a wide spectrum of tasks and data by providing scalable solutions for diverse resource constraints and deployment scenarios.

Enhancing existing models with new knowledge is a crucial aspect of AI development. This paper introduces a novel method for integrating a new language into a large language model (LLM). Our approach successfully incorporates a previously unseen target language into an existing LLM without compromising its prior knowledge. We trained a tiny model with 1.5 billion parameters named Kuwain by injecting the Arabic language into a small open-source model mainly trained in English. Our method demonstrates significant improvements in Arabic language performance, with an average 8% improvement across various benchmarks, while retaining the model's existing knowledge with a minimum amount of the original model's data. This offers a cost-effective alternative to training a comprehensive model in both English and Arabic. The results highlight the potential for efficient, targeted language model expansion without extensive retraining or resource-intensive processes.

Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control. However, they remain fundamentally limited in tasks that require high precision due to their single-inference paradigm. While test-time scaling approaches using external verifiers have shown promise, they require additional training and fail to generalize to unseen conditions. We propose Masking Distribution Guided Selection (MG-Select), a novel test-time scaling framework for VLAs that leverages the model's internal properties without requiring additional training or external modules. Our approach utilizes KL divergence from a reference action token distribution as a confidence metric for selecting the optimal action from multiple candidates. We introduce a reference distribution generated by the same VLA but with randomly masked states and language conditions as inputs, ensuring maximum uncertainty while remaining aligned with the target task distribution. Additionally, we propose a joint training strategy that enables the model to learn both conditional and unconditional distributions by applying dropout to state and language conditions, thereby further improving the quality of the reference distribution. Our experiments demonstrate that MG-Select achieves significant performance improvements, including a 28%/35% improvement in real-world in-distribution/out-of-distribution tasks, along with a 168% relative gain on RoboCasa pick-and-place tasks trained with 30 demonstrations.

Dual-encoder retrievers depend on the principle that relevant documents should score higher than irrelevant ones for a given query. Yet the dominant Noise Contrastive Estimation (NCE) objective, which underpins Contrastive Loss, optimizes a softened ranking surrogate that we rigorously prove is fundamentally oblivious to score separation quality and unrelated to AUC. This mismatch leads to poor calibration and suboptimal performance in downstream tasks like retrieval-augmented generation (RAG). To address this fundamental limitation, we introduce the MW loss, a new training objective that maximizes the Mann-Whitney U statistic, which is mathematically equivalent to the Area under the ROC Curve (AUC). MW loss encourages each positive-negative pair to be correctly ranked by minimizing binary cross entropy over score differences. We provide theoretical guarantees that MW loss directly upper-bounds the AoC, better aligning optimization with retrieval goals. We further promote ROC curves and AUC as natural threshold free diagnostics for evaluating retriever calibration and ranking quality. Empirically, retrievers trained with MW loss consistently outperform contrastive counterparts in AUC and standard retrieval metrics. Our experiments show that MW loss is an empirically superior alternative to Contrastive Loss, yielding better-calibrated and more discriminative retrievers for high-stakes applications like RAG.

We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops foundational text and vision understanding, then enhances visual reasoning through targeted synthetic data generation addressing spatial structure, compositional understanding, and fine-grained perception, and (3) high-quality text-only supervised fine-tuning on curated instruction-response pairs with explicit reasoning traces spanning mathematics, coding, science, and tool use. Notably, our model achieves competitive results without reinforcement learning or preference optimization, isolating the contribution of our data-centric continual pre-training approach. On the Artificial Analysis Intelligence Index, Apriel-1.5-15B-Thinker attains a score of 52, matching DeepSeek-R1-0528 despite requiring significantly fewer computational resources. Across ten image benchmarks, its performance is on average within five points of Gemini-2.5-Flash and Claude Sonnet-3.7, a key achievement for a model operating within single-GPU deployment constraints. Our results demonstrate that thoughtful mid-training 2 design can close substantial capability gaps without massive scale, making frontier-level multimodal reasoning accessible to organizations with limited infrastructure. We release the model checkpoint, all training recipes, and evaluation protocols under the MIT license to to advance open-source research.

jina-reranker-v3 is a 0.6B parameter multilingual document reranker that introduces a novel last but not late interaction. Unlike late interaction models such as ColBERT that perform separate encoding followed by multi-vector matching, our approach conducts causal self-attention between query and documents within the same context window, enabling rich cross-document interactions before extracting contextual embeddings from the last token of each document. This compact architecture achieves state-of-the-art BEIR performance with 61.94 nDCG@10 while being ten times smaller than generative listwise rerankers.

Vision-Language Models (VLMs) excel at high-level scene understanding but falter on fine-grained perception tasks requiring precise localization. This failure stems from a fundamental mismatch, as generating exact numerical coordinates is a challenging task for language-centric architectures. In this paper, we introduce VLM-FO1, a novel framework that overcomes this limitation by reframing object-centric perception from a brittle coordinate generation problem into a robust feature retrieval task. Our method operates as a plug-and-play module that integrates with any pre-trained VLM. It leverages a Hybrid Fine-grained Region Encoder (HFRE), featuring a dual vision encoder, to generate powerful region tokens rich in both semantic and spatial detail. A token-based referencing system then enables the LLM to seamlessly reason about and ground language in these specific visual regions. Experiments show that VLM-FO1 achieves state-of-the-art performance across a diverse suite of benchmarks, demonstrating exceptional capabilities in object grounding, region generational understanding, and visual region reasoning. Crucially, our two-stage training strategy ensures that these perception gains are achieved without compromising the base model's general visual understanding capabilities. VLM-FO1 establishes an effective and flexible paradigm for building perception-aware VLMs, bridging the gap between high-level reasoning and fine-grained visual grounding.

We introduce Mutarjim, a compact yet powerful language model for bidirectional Arabic-English translation. While large-scale LLMs have shown impressive progress in natural language processing tasks, including machine translation, smaller models. Leveraging this insight, we developed Mutarjim based on Kuwain-1.5B , a language model tailored for both Arabic and English. Despite its modest size, Mutarjim outperforms much larger models on several established benchmarks, achieved through an optimized two-phase training approach and a carefully curated, high-quality training corpus.. Experimental results show that Mutarjim rivals models up to 20 times larger while significantly reducing computational costs and training requirements. We also introduce Tarjama-25, a new benchmark designed to overcome limitations in existing Arabic-English benchmarking datasets, such as domain narrowness, short sentence lengths, and English-source bias. Tarjama-25 comprises 5,000 expert-reviewed sentence pairs and spans a wide range of domains, offering a more comprehensive and balanced evaluation framework. Notably, Mutarjim achieves state-of-the-art performance on the English-to-Arabic task in Tarjama-25, surpassing even significantly larger and proprietary models like GPT-4o mini. We publicly release Tarjama-25 to support future research and advance the evaluation of Arabic-English translation systems.

We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow combines an insertion-based Edit Flow for discrete text tokens with Flow Matching for image latents. OneFlow enables concurrent text-image synthesis with hierarchical sampling that prioritizes content over grammar. Through controlled experiments across model sizes from 1B to 8B, we demonstrate that OneFlow outperforms autoregressive baselines on both generation and understanding tasks while using up to 50% fewer training FLOPs. OneFlow surpasses both autoregressive and diffusion-based approaches while unlocking new capabilities for concurrent generation, iterative refinement, and natural reasoning-like generation.

Visual personalization is essential in user-facing AI systems such as smart homes and healthcare, where aligning model behavior with user-centric concepts is critical. However, recent large Vision-Language Models (VLMs), despite their broad applicability, remain underexplored in their ability to adapt to individual users. In this paper, we introduce MMPB, the first extensive benchmark for evaluating VLMs on personalization. MMPB comprises 10k image-query pairs and includes 111 personalizable concepts across four categories: humans, animals, objects, and characters, with the human category enriched with preference-grounded queries. We structure personalization into three main task types, each highlighting a different key property of VLMs. Using 23 widely used VLMs including both open- and closed-source models, we evaluate personalization performance via a three-stage protocol: concept injection, multi-turn dialogue, and personalized querying. Our findings indicate that most VLMs (including some closed-source models) struggle with personalization, particularly in maintaining consistency over dialogue, handling user preferences, and adapting to visual cues. Our analysis reveals that the challenges in VLM personalization (such as refusal behaviors and long-context forgetting) highlight substantial room for improvement. By identifying these limitations and offering a scalable benchmark, MMPB offers valuable insights and a solid foundation for future research toward truly personalized multi-modal AI. Project Page: aidaslab.github.io/MMPB

We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can be learned from training on static code alone, we mid-train CWM on a large amount of observation-action trajectories from Python interpreter and agentic Docker environments, and perform extensive multi-task reasoning RL in verifiable coding, math, and multi-turn software engineering environments. With CWM, we provide a strong testbed for researchers to explore the opportunities world modeling affords for improving code generation with reasoning and planning in computational environments. We present first steps of how world models can benefit agentic coding, enable step-by-step simulation of Python code execution, and show early results of how reasoning can benefit from the latter. CWM is a dense, decoder-only LLM trained with a context size of up to 131k tokens. Independent of its world modeling capabilities, CWM offers strong performance on general coding and math tasks: it reaches pass@1 scores of 65.8% on SWE-bench Verified (with test-time scaling), 68.6% on LiveCodeBench, 96.6% on Math-500, and 76.0% on AIME 2024. To support further research on code world modeling, we release model checkpoints after mid-training, SFT, and RL.

Despite advances in multilingual automatic speech recognition (ASR), code-switching (CS), the mixing of languages within an utterance common in daily speech, remains a severely underexplored challenge. In this paper, we introduce HiKE: the Hierarchical Korean-English code-switching benchmark, the first globally accessible evaluation framework for Korean-English CS, aiming to provide a means for the precise evaluation of multilingual ASR models and to foster research in the field. The proposed framework not only consists of high-quality, natural CS data across various topics, but also provides meticulous loanword labels and a hierarchical CS-level labeling scheme (word, phrase, and sentence) that together enable a systematic evaluation of a model's ability to handle each distinct level of code-switching. Through evaluations of diverse multilingual ASR models and fine-tuning experiments, this paper demonstrates that while most multilingual ASR models initially struggle with CS-ASR, this capability can be enabled through fine-tuning with CS data. HiKE will be available at https://github.com/ThetaOne-AI/HiKE.

Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for high-resource languages, their performance on Arabic remains limited. In this work, we introduce Baseer, a vision-language model fine- tuned specifically for Arabic document OCR. Leveraging a large-scale dataset combining synthetic and real-world documents, Baseer is trained using a decoder-only fine-tuning strategy to adapt a pre-trained MLLM while preserving general visual features. We also present Misraj-DocOCR, a high-quality, expert-verified benchmark designed for rigorous evaluation of Arabic OCR systems. Our experiments show that Baseer significantly outperforms existing open-source and commercial solutions, achieving a WER of 0.25 and establishing a new state-of-the-art in the domain of Arabic document OCR. Our results highlight the benefits of domain-specific adaptation of general-purpose MLLMs and establish a strong baseline for high-accuracy OCR on morphologically rich languages like Arabic.

Tool-integrated reasoning has emerged as a key focus for enabling agentic applications. Among these, DeepResearch Agents have gained significant attention for their strong performance on complex, open-ended information-seeking tasks. We introduce Fathom-DeepResearch, an agentic system composed of two specialized models. The first is Fathom-Search-4B, a DeepSearch model trained from Qwen3-4B and optimized for evidence-based investigation through live web search and targeted webpage querying. Its training combines three advances: (i) DUETQA, a 5K-sample dataset generated via multi-agent self-play that enforces strict web-search dependence and heterogeneous source grounding; (ii) RAPO, a zero-overhead extension of GRPO that stabilizes multi-turn Reinforcement Learning with Verifiable Rewards through curriculum pruning, reward-aware advantage scaling, and per-prompt replay buffers; and (iii) a steerable step-level reward that classifies each tool call by cognitive behavior and marginal utility, enabling explicit control over search trajectory breadth, depth, and horizon. These improvements enable reliable extension of tool-calling beyond 20 calls when warranted. The second is Fathom-Synthesizer-4B, trained from Qwen3-4B, which converts multi-turn DeepSearch traces into structured, citation-dense DeepResearch Reports for comprehensive synthesis. Evaluated on DeepSearch benchmarks (SimpleQA, FRAMES, WebWalker, Seal0, MuSiQue) and DeepResearch-Bench, the system achieves state-of-the-art performance in the open-weights category while demonstrating strong generalization to diverse reasoning tasks including HLE, AIME-25, GPQA-Diamond, and MedQA.

We posit that to achieve continual model improvement and multifaceted alignment, future models must learn from natural human interaction. Current conversational models are aligned using pre-annotated, expert-generated human feedback. In this work, we introduce Reinforcement Learning from Human Interaction (RLHI), a paradigm that learns directly from in-the-wild user conversations. We develop two complementary methods: (1) RLHI with User-Guided Rewrites, which revises unsatisfactory model outputs based on users' natural-language follow-up responses, (2) RLHI with User-Based Rewards, which learns via a reward model conditioned on knowledge of the user's long-term interaction history (termed persona). Together, these methods link long-term user personas to turn-level preferences via persona-conditioned preference optimization. Trained on conversations derived from WildChat, both RLHI variants outperform strong baselines in personalization and instruction-following, and similar feedback enhances performance on reasoning benchmarks. These results suggest organic human interaction offers scalable, effective supervision for personalized alignment.

Distribution matching is central to many vision and graphics tasks, where the widely used Wasserstein distance is too costly to compute for high dimensional distributions. The Sliced Wasserstein Distance (SWD) offers a scalable alternative, yet its Monte Carlo estimator suffers from high variance, resulting in noisy gradients and slow convergence. We introduce Reservoir SWD (ReSWD), which integrates Weighted Reservoir Sampling into SWD to adaptively retain informative projection directions in optimization steps, resulting in stable gradients while remaining unbiased. Experiments on synthetic benchmarks and real-world tasks such as color correction and diffusion guidance show that ReSWD consistently outperforms standard SWD and other variance reduction baselines. Project page: https://reservoirswd.github.io/

Distilling the thinking traces of a Large Language Model (LLM) with reasoning capabilities into a smaller model has been proven effective. Yet, there is a scarcity of work done on how model performances scale with the quantity of distillation data. In this work, we study the scaling trend of distilling competitive coding skills on two small non-reasoning LLMs. We validate the hypothesis that there is a valley of code reasoning: downstream performance on competitive coding first drops as data quantity increases, then it steadily increases in a sharper-than-log-linear fashion. Having identified the trend, we further fine-tune the models at two different distillation stages on the same data to ground conclusions on their respective learning phases. We learn that across stages in the low and medium-low data regimes, small models benefit significantly from easier coding questions than from harder ones. We also find that, surprisingly, the correctness of outputs in training data makes no difference to distillation outcomes. Our work represents a step forward in understanding the training dynamics of code reasoning distillation outside intuition

Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings. A shared latent working memory then preserves and transfers each agent's internal representations, ensuring lossless information exchange. We provide theoretical analyses establishing that LatentMAS attains higher expressiveness and lossless information preservation with substantially lower complexity than vanilla text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS consistently outperforms strong single-model and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4x-4.3x faster end-to-end inference. These results demonstrate that our new latent collaboration framework enhances system-level reasoning quality while offering substantial efficiency gains without any additional training. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS.

Low-rank adaptations (LoRA) are often employed to fine-tune large language models (LLMs) for new tasks. This paper investigates LoRA composability for cross-task generalization and introduces LoraHub, a strategic framework devised for the purposive assembly of LoRA modules trained on diverse given tasks, with the objective of achieving adaptable performance on unseen tasks. With just a few examples from a novel task, LoraHub enables the fluid combination of multiple LoRA modules, eradicating the need for human expertise. Notably, the composition requires neither additional model parameters nor gradients. Our empirical results, derived from the Big-Bench Hard (BBH) benchmark, suggest that LoraHub can effectively mimic the performance of in-context learning in few-shot scenarios, excluding the necessity of in-context examples alongside each inference input. A significant contribution of our research is the fostering of a community for LoRA, where users can share their trained LoRA modules, thereby facilitating their application to new tasks. We anticipate this resource will widen access to and spur advancements in general intelligence as well as LLMs in production. Code will be available at https://github.com/sail-sg/lorahub.

The Transformer architecture has become the de facto standard for Large Language Models (LLMs), demonstrating remarkable capabilities in language understanding and generation. However, its application in conversational AI is fundamentally constrained by its stateless nature and the quadratic computational complexity (O(L^2)) with respect to sequence length L. Current models emulate memory by reprocessing an ever-expanding conversation history with each turn, leading to prohibitive costs and latency in long dialogues. This paper introduces the Reactive Transformer (RxT), a novel architecture designed to overcome these limitations by shifting from a data-driven to an event-driven paradigm. RxT processes each conversational turn as a discrete event in real-time, maintaining context in an integrated, fixed-size Short-Term Memory (STM) system. The architecture features a distinct operational cycle where a generator-decoder produces a response based on the current query and the previous memory state, after which a memory-encoder and a dedicated Memory Attention network asynchronously update the STM with a representation of the complete interaction. This design fundamentally alters the scaling dynamics, reducing the total user-facing cost of a conversation from quadratic (O(N^2 cdot T)) to linear (O(N cdot T)) with respect to the number of interactions N. By decoupling response generation from memory updates, RxT achieves low latency, enabling truly real-time, stateful, and economically viable long-form conversations. We validated our architecture with a series of proof-of-concept experiments on synthetic data, demonstrating superior performance and constant-time inference latency compared to a baseline stateless model of comparable size.

We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingual representation. Unlike many prior models that release weights without reproducible data pipelines or regard for content-owner rights, Apertus models are pretrained exclusively on openly available data, retroactively respecting robots.txt exclusions and filtering for non-permissive, toxic, and personally identifiable content. To mitigate risks of memorization, we adopt the Goldfish objective during pretraining, strongly suppressing verbatim recall of data while retaining downstream task performance. The Apertus models also expand multilingual coverage, training on 15T tokens from over 1800 languages, with ~40% of pretraining data allocated to non-English content. Released at 8B and 70B scales, Apertus approaches state-of-the-art results among fully open models on multilingual benchmarks, rivalling or surpassing open-weight counterparts. Beyond model weights, we release all scientific artifacts from our development cycle with a permissive license, including data preparation scripts, checkpoints, evaluation suites, and training code, enabling transparent audit and extension.

Recent works on context and memory benchmarking have primarily focused on conversational instances but the need for evaluating memory in dynamic enterprise environments is crucial for its effective application. We introduce MEMTRACK, a benchmark designed to evaluate long-term memory and state tracking in multi-platform agent environments. MEMTRACK models realistic organizational workflows by integrating asynchronous events across multiple communication and productivity platforms such as Slack, Linear and Git. Each benchmark instance provides a chronologically platform-interleaved timeline, with noisy, conflicting, cross-referring information as well as potential codebase/file-system comprehension and exploration. Consequently, our benchmark tests memory capabilities such as acquistion, selection and conflict resolution. We curate the MEMTRACK dataset through both manual expert driven design and scalable agent based synthesis, generating ecologically valid scenarios grounded in real world software development processes. We introduce pertinent metrics for Correctness, Efficiency, and Redundancy that capture the effectiveness of memory mechanisms beyond simple QA performance. Experiments across SoTA LLMs and memory backends reveal challenges in utilizing memory across long horizons, handling cross-platform dependencies, and resolving contradictions. Notably, the best performing GPT-5 model only achieves a 60\% Correctness score on MEMTRACK. This work provides an extensible framework for advancing evaluation research for memory-augmented agents, beyond existing focus on conversational setups, and sets the stage for multi-agent, multi-platform memory benchmarking in complex organizational settings

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks when equipped with external tools. However, current frameworks predominantly rely on sequential processing, leading to inefficient execution particularly for tasks requiring extensive tool interaction. This paper introduces Flash-Searcher, a novel parallel agent reasoning framework that fundamentally reimagines the execution paradigm from sequential chains to directed acyclic graphs (DAGs). Flash-Searcher decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths while maintaining logical constraints. Through dynamic workflow optimization, our framework continuously refines the execution graph based on intermediate results, effectively integrating summary module. Comprehensive evaluations across multiple benchmarks demonstrate that Flash-Searcher consistently outperforms existing approaches. Specifically, it achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks. Furthermore, when distilling this parallel reasoning pipeline into single models, we observe substantial performance gains across diverse backbone architectures, underscoring the generalizability of our methodology. Our work thus represents a significant advance in agent architecture design, offering a more scalable and efficient paradigm for complex reasoning tasks.

Efficient detectors for edge devices are often optimized for parameters or speed count metrics, which remain in weak correlation with the energy of detectors. However, some vision applications of convolutional neural networks, such as always-on surveillance cameras, are critical for energy constraints. This paper aims to serve as a baseline by designing detectors to reach tradeoffs between energy and performance from two perspectives: 1) We extensively analyze various CNNs to identify low-energy architectures, including selecting activation functions, convolutions operators, and feature fusion structures on necks. These underappreciated details in past work seriously affect the energy consumption of detectors; 2) To break through the dilemmatic energy-performance problem, we propose a balanced detector driven by energy using discovered low-energy components named FemtoDet. In addition to the novel construction, we improve FemtoDet by considering convolutions and training strategy optimizations. Specifically, we develop a new instance boundary enhancement (IBE) module for convolution optimization to overcome the contradiction between the limited capacity of CNNs and detection tasks in diverse spatial representations, and propose a recursive warm-restart (RecWR) for optimizing training strategy to escape the sub-optimization of light-weight detectors by considering the data shift produced in popular augmentations. As a result, FemtoDet with only 68.77k parameters achieves a competitive score of 46.3 AP50 on PASCAL VOC and 1.11 W & 64.47 FPS on Qualcomm Snapdragon 865 CPU platforms. Extensive experiments on COCO and TJU-DHD datasets indicate that the proposed method achieves competitive results in diverse scenes.

Test-Driven Development (TDD) is a widely adopted software engineering practice that requires developers to create and execute tests alongside code implementation, ensuring that software behavior is continuously validated and refined. In the era of vibe coding, where developers increasingly delegate code writing to large language models (LLMs) by specifying high-level intentions, TDD becomes even more crucial, as test cases serve as executable specifications that explicitly define and verify intended functionality beyond what natural-language descriptions and code context can convey. While vibe coding under TDD is promising, there are three main challenges: (1) selecting a small yet effective test suite to improve the generation accuracy and control the execution workload, (2) retrieving context such as relevant code effectively, and (3) systematically using test feedback for effective code refinement. To address these challenges, we introduce TENET, an LLM agent for generating functions in complex real-world repositories under the TDD setting. TENET features three components: (1) a novel test harness mechanism that selects a concise test suite to maximize diversity of target usage scenarios; (2) a tailored agent toolset that performs efficient retrieval of relevant code with interactive debugging; and (3) a reflection-based refinement workflow that iteratively analyzes failures, replenishes context, and applies code refinement. TENET achieves 69.08% and 81.77% Pass@1 on RepoCod and RepoEval benchmarks, outperforming the best agentic baselines by 9.49 and 2.17 percentage points, respectively. In addition, this is the first study of test-driven code generation with repository-level context, examining how different aspects of test suites affect the performance of LLM agents under the TDD setting.

Using proprietary Large Language Models on legal tasks poses challenges due to data privacy issues, domain data heterogeneity, domain knowledge sophistication, and domain objectives uniqueness. We created Aalalp, a fine-tuned Mistral 7B model on instructions data related to specific Indian legal tasks. The performance of Aalap is better than gpt-3.5-turbo in 31\% of our test data and obtains an equivalent score in 34\% of the test data as evaluated by GPT4. Training Aalap mainly focuses on teaching legal reasoning rather than legal recall. Aalap is definitely helpful for the day-to-day activities of lawyers, judges, or anyone working in legal systems.

This study evaluates Artificial Intelligence (AI) agents for Dhumbal, a culturally significant multiplayer card game with imperfect information, through a systematic comparison of rule-based, search-based, and learning-based strategies. We formalize Dhumbal's mechanics and implement diverse agents, including heuristic approaches (Aggressive, Conservative, Balanced, Opportunistic), search-based methods such as Monte Carlo Tree Search (MCTS) and Information Set Monte Carlo Tree Search (ISMCTS), and reinforcement learning approaches including Deep Q-Network (DQN) and Proximal Policy Optimization (PPO), and a random baseline. Evaluation involves within-category tournaments followed by a cross-category championship. Performance is measured via win rate, economic outcome, Jhyap success, cards discarded per round, risk assessment, and decision efficiency. Statistical significance is assessed using Welch's t-test with Bonferroni correction, effect sizes via Cohen's d, and 95% confidence intervals (CI). Across 1024 simulated rounds, the rule-based Aggressive agent achieves the highest win rate (88.3%, 95% CI: [86.3, 90.3]), outperforming ISMCTS (9.0%) and PPO (1.5%) through effective exploitation of Jhyap declarations. The study contributes a reproducible AI framework, insights into heuristic efficacy under partial information, and open-source code, thereby advancing AI research and supporting digital preservation of cultural games.

The diffusion MRI Neurite Exchange Imaging model offers a promising framework for probing gray matter microstructure by estimating parameters such as compartment sizes, diffusivities, and inter-compartmental water exchange time. However, existing protocols require long scan times. This study proposes a reduced acquisition scheme for the Connectome 2.0 scanner that preserves model accuracy while substantially shortening scan duration. We developed a data-driven framework using explainable artificial intelligence with a guided recursive feature elimination strategy to identify an optimal 8-feature subset from a 15-feature protocol. The performance of this optimized protocol was validated in vivo and benchmarked against the full acquisition and alternative reduction strategies. Parameter accuracy, preservation of anatomical contrast, and test-retest reproducibility were assessed. The reduced protocol yielded parameter estimates and cortical maps comparable to the full protocol, with low estimation errors in synthetic data and minimal impact on test-retest variability. Compared to theory-driven and heuristic reduction schemes, the optimized protocol demonstrated superior robustness, reducing the deviation in water exchange time estimates by over two-fold. In conclusion, this hybrid optimization framework enables viable imaging of neurite exchange in 14 minutes without loss of parameter fidelity. This approach supports the broader application of exchange-sensitive diffusion magnetic resonance imaging in neuroscience and clinical research, and offers a generalizable method for designing efficient acquisition protocols in biophysical parameter mapping.

As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and efficiency. We present the first work towards understanding this new system design space for multi-modal text-to-image (TTI) and text-to-video (TTV) generation models. Current model architecture designs are bifurcated into 2 categories: Diffusion- and Transformer-based models. Our systematic performance characterization on a suite of eight representative TTI/TTV models shows that after state-of-the-art optimization techniques such as Flash Attention are applied, Convolution accounts for up to 44% of execution time for Diffusion-based TTI models, while Linear layers consume up to 49% of execution time for Transformer-based models. We additionally observe that Diffusion-based TTI models resemble the Prefill stage of LLM inference, and benefit from 1.1-2.5x greater speedup from Flash Attention than Transformer-based TTI models that resemble the Decode phase. Since optimizations designed for LLMs do not map directly onto TTI/TTV models, we must conduct a thorough characterization of these workloads to gain insights for new optimization opportunities. In doing so, we define sequence length in the context of TTI/TTV models and observe sequence length can vary up to 4x in Diffusion model inference. We additionally observe temporal aspects of TTV workloads pose unique system bottlenecks, with Temporal Attention accounting for over 60% of total Attention time. Overall, our in-depth system performance characterization is a critical first step towards designing efficient and deployable systems for emerging TTI/TTV workloads.

Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify the risks of malicious misuse cases such as unauthorized collection of personally identifiable information (PII), generation of socially divisive content, and even automated web hacking. To address these threats, we propose an AI Kill Switch technique that can immediately halt the operation of malicious web-based LLM agents. To achieve this, we introduce AutoGuard - the key idea is generating defensive prompts that trigger the safety mechanisms of malicious LLM agents. In particular, generated defense prompts are transparently embedded into the website's DOM so that they remain invisible to human users but can be detected by the crawling process of malicious agents, triggering its internal safety mechanisms to abort malicious actions once read. To evaluate our approach, we constructed a dedicated benchmark consisting of three representative malicious scenarios (PII collection, social rift content generation, and web hacking attempts). Experimental results show that the AutoGuard method achieves over 80% Defense Success Rate (DSR) on malicious agents, including GPT-4o, Claude-3, and Llama3.3-70B-Instruct. It also maintains strong performance, achieving around 90% DSR on GPT-5, GPT-4.1, and Gemini-2.5-Flash when used as the malicious agent, demonstrating robust generalization across models and scenarios. Through this research, we have demonstrated the controllability of web-based LLM agents across various scenarios and models, thereby contributing to the broader effort of AI control and safety.

Background: Emerging reports of "AI psychosis" are on the rise, where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms. Whilst the sycophantic and agreeable nature of LLMs can be beneficial, it becomes a vector for harm by reinforcing delusional beliefs in vulnerable users. Methods: Psychosis-bench is a novel benchmark designed to systematically evaluate the psychogenicity of LLMs comprises 16 structured, 12-turn conversational scenarios simulating the progression of delusional themes(Erotic Delusions, Grandiose/Messianic Delusions, Referential Delusions) and potential harms. We evaluated eight prominent LLMs for Delusion Confirmation (DCS), Harm Enablement (HES), and Safety Intervention(SIS) across explicit and implicit conversational contexts. Findings: Across 1,536 simulated conversation turns, all LLMs demonstrated psychogenic potential, showing a strong tendency to perpetuate rather than challenge delusions (mean DCS of 0.91 pm0.88). Models frequently enabled harmful user requests (mean HES of 0.69 pm0.84) and offered safety interventions in only roughly a third of applicable turns (mean SIS of 0.37 pm0.48). 51 / 128 (39.8%) of scenarios had no safety interventions offered. Performance was significantly worse in implicit scenarios, models were more likely to confirm delusions and enable harm while offering fewer interventions (p < .001). A strong correlation was found between DCS and HES (rs = .77). Model performance varied widely, indicating that safety is not an emergent property of scale alone. Conclusion: This study establishes LLM psychogenicity as a quantifiable risk and underscores the urgent need for re-thinking how we train LLMs. We frame this issue not merely as a technical challenge but as a public health imperative requiring collaboration between developers, policymakers, and healthcare professionals.

Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty. Because these challenges will persist even as LLM technology improves, we argue that any automated annotation process using an LLM must validate the LLM's performance against labels generated by humans. To this end, we outline a workflow to harness the annotation potential of LLMs in a principled, efficient way. Using GPT-4, we validate this approach by replicating 27 annotation tasks across 11 datasets from recent social science articles in high-impact journals. We find that LLM performance for text annotation is promising but highly contingent on both the dataset and the type of annotation task, which reinforces the necessity to validate on a task-by-task basis. We make available easy-to-use software designed to implement our workflow and streamline the deployment of LLMs for automated annotation.

The integration of Large Language Models (LLMs) into healthcare holds significant potential to enhance diagnostic accuracy and support medical treatment planning. These AI-driven systems can analyze vast datasets, assisting clinicians in identifying diseases, recommending treatments, and predicting patient outcomes. This study evaluates the performance of a range of contemporary LLMs, including both open-source and closed-source models, on the 2024 Portuguese National Exam for medical specialty access (PNA), a standardized medical knowledge assessment. Our results highlight considerable variation in accuracy and cost-effectiveness, with several models demonstrating performance exceeding human benchmarks for medical students on this specific task. We identify leading models based on a combined score of accuracy and cost, discuss the implications of reasoning methodologies like Chain-of-Thought, and underscore the potential for LLMs to function as valuable complementary tools aiding medical professionals in complex clinical decision-making.