Trending Papers

Wan-Move enhances motion control in video generative models by integrating motion-aware features into latent space, enabling high-quality and scalable video synthesis.

Z-Image, a 6B-parameter Scalable Single-Stream Diffusion Transformer (S3-DiT) model, achieves high-performance image generation with reduced computational cost, offering sub-second inference and compatibility with consumer hardware.

The study reveals that in text-to-image generation, CFG Augmentation is the primary driver of few-step distillation in Distribution Matching Distillation (DMD), while the distribution matching term acts as a regularizer.

Live Avatar uses a 14-billion-parameter diffusion model with Timestep-forcing Pipeline Parallelism and Rolling Sink Frame Mechanism to achieve real-time, high-fidelity avatar generation.

PaperDebugger is an in-editor academic writing assistant that integrates large language models, enabling direct interaction within LaTeX editors for document state management, revision, and literature search.

TwinFlow is a 1-step generative model framework that enhances inference efficiency without requiring fixed pretrained teacher models or standard adversarial networks, achieving high performance on text-to-image tasks and scaling efficiently.

DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.

LongCat-Image is a bilingual open-source foundation model for image generation that addresses multilingual text rendering, photorealism, and deployment efficiency through rigorous data curation, compact design, and comprehensive open-source support.

Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.

RealGen is a photorealistic text-to-image framework that uses an LLM for prompt optimization and a diffusion model for image generation, enhanced by a Detector Reward mechanism and RealBench for automated evaluation.

LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.

Semantic-First Diffusion (SFD) enhances image generation by asynchronously denoising semantic and texture latents, improving convergence and quality.

MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy.

MinerU is an open-source tool that enhances document content extraction using fine-tuned models and pre/postprocessing rules across diverse document types.

PaddleOCR-VL, a vision-language model combining NaViT-style dynamic resolution and ERNIE, achieves state-of-the-art performance in document parsing and element recognition with high efficiency.

MVP, a scalable multi-view transformer architecture, efficiently reconstructs large 3D scenes from multiple images using dual hierarchies and achieves state-of-the-art quality.

SAM 3D is a generative model that reconstructs 3D objects from single images using a multi-stage training framework that includes synthetic pretraining and real-world alignment, achieving high performance in human preference tests.

LlamaFactory is a unified framework enabling efficient fine-tuning of large language models across various tasks using a web-based user interface.

A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio.

OneThinker, an all-in-one multimodal reasoning model, unifies image and video understanding across various tasks using RL and demonstrates strong performance and knowledge transfer.

DAComp is a benchmark of 210 tasks that evaluates the capabilities of agents in real-world data engineering and data analysis workflows, revealing significant deficiencies in both areas.

A novel GPT-based model, OmniFlatten, enables real-time natural full-duplex spoken dialogue through a multi-stage post-training technique that integrates speech and text without altering the original model's architecture.

Depth Anything 3 (DA3) uses a plain transformer for geometry prediction from visual inputs, achieving state-of-the-art results in camera pose estimation, any-view geometry, visual rendering, and monocular depth estimation.

IndexTTS, an enhanced text-to-speech system combining XTTS and Tortoise models, offers improved naturalness, enhanced voice cloning, and controllable usage through hybrid character-pinyin modeling and optimized vector quantization.

Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.

Zep, a memory layer service, outperforms MemGPT in the DMR benchmark and LongMemEval by excelling in dynamic knowledge integration and temporal reasoning, critical for enterprise use cases.

A vision-language model (VLM) named GLM-4.1V-Thinking, developed with a reasoning-centric training framework, achieves state-of-the-art performance across various tasks, including STEM problem solving, video understanding, and long document understanding, outperforming larger models on many benchmarks.

UI-TARS, a native GUI agent model using screenshots as input, outperforms commercial models in various benchmarks through enhanced perception, unified action modeling, system-2 reasoning, and iterative training with reflective online traces.

MobiAgent, a comprehensive mobile agent system, achieves state-of-the-art performance in real-world mobile scenarios through its MobiMind-series models, AgentRR framework, and MobiFlow benchmarking suite, while also reducing data annotation costs.

RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.

A framework called Easy Dataset synthesizes fine-tuning data from unstructured documents using a GUI and LLMs, improving domain-specific performance of LLMs while maintaining general knowledge.

DeepAnalyze-8B, an agentic LLM, autonomously completes the data science pipeline from raw data to research reports using curriculum-based training and data-grounded trajectory synthesis.

UnityVideo, a unified framework, enhances video generation by integrating multiple modalities and paradigms, leading to improved quality and alignment with real-world constraints.

VideoCoF, a Chain-of-Frames approach, improves video editing precision and instruction-to-region mapping by using reasoning tokens without requiring user-provided masks.

Agent Lightning is a flexible RL framework for training LLMs in various agents, using a hierarchical RL algorithm and decoupling execution from training to handle complex interactions.

InternVL3 is a multimodal pre-trained language model that jointly learns from both multimodal data and text, improving performance and scalability through advanced techniques and setting a new state-of-the-art in multimodal tasks.

GigaBrain-0, a VLA foundation model, uses world model-generated data to enhance cross-task generalization and policy robustness, improving real-world performance on complex manipulation tasks.

Flawed-Aware Policy Optimization (FAPO) enhances reinforcement learning with verifiable rewards by penalizing flawed-positive rollouts, improving reasoning capability and training stability in large language models.

ReCamDriving generates camera-controlled novel-trajectory videos using dense 3DGS renderings and a two-stage training approach, achieving state-of-the-art results in controllability and consistency.

A vision-action policy using correlated noise for flow matching and learnable mixed-layer attention wins the 2025 BEHAVIOR Challenge with high performance across diverse household tasks.

CLaRa enhances retrieval-augmented generation by introducing unified embedding-based compression and joint optimization, achieving state-of-the-art performance in QA benchmarks.

This survey explores the application, performance, and challenges of large language models in medical settings, offering guidelines for their practical use.

The paper introduces Reward Forcing, which enhances video generation by updating sink tokens with EMA-Sink and using Rewarded Distribution Matching Distillation to prioritize dynamic content.

AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe development and deployment.

GRAPE is a unified positional encoding framework that combines multiplicative rotations and additive logit biases, extending existing methods like RoPE and ALiBi.

PPTAgent, a two-stage approach, improves presentation generation by analyzing reference presentations and ensuring structural and content consistency, outperforming traditional methods across content, design, and coherence.

PyTorch Fully Sharded Data Parallel (FSDP) enables efficient and scalable training of large models across hardware configurations.

EgoEdit is a real-time, instruction-following egocentric video editor that addresses challenges in handling egomotion and hand-object interactions, outperforming existing methods on egocentric editing tasks.

A simple head-specific sigmoid gate applied after Scaled Dot-Product Attention improves performance, stability, and scaling in large models, mitigating 'attention sink' and enhancing long-context extrapolation.

NEO, a novel family of native Vision-Language Models, addresses fundamental constraints and integrates vision and language within a unified framework, achieving competitive performance with limited data.