In-Context Representation Hijacking
Paper • 2512.03771 • Published • 4
AI & ML interests
None defined yet.
yossig
authored a
paper 4 months ago
pogchamp
authored a
paper 4 months ago
hvoss-techfak
authored 7
papers 5 months ago
Real-Time Inverse Kinematics for Generating Multi-Constrained Movements of Virtual Human Characters
Paper • 2507.00792 • Published • 1
ImaGGen: Zero-Shot Generation of Co-Speech Semantic Gestures Grounded in Language and Image Input
Paper • 2510.17617 • Published • 1
Conveying Meaning through Gestures: An Investigation into Semantic Co-Speech Gesture Generation
Paper • 2510.17599 • Published • 1
Integrating Representational Gestures into Automatically Generated Embodied Explanations and its Effects on Understanding and Interaction Quality
Paper • 2406.12544 • Published
Augmented Co-Speech Gesture Generation: Including Form and Meaning Features to Guide Learning-Based Gesture Synthesis
Paper • 2307.09597 • Published
AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis
Paper • 2305.01241 • Published
Addressing Data Scarcity in Multimodal User State Recognition by Combining Semi-Supervised and Supervised Learning
Paper • 2202.03775 • Published
mbrack
authored a
paper 5 months ago
pogchamp
authored 5
papers 7 months ago
Merlin: A Vision Language Foundation Model for 3D Computed Tomography
Paper • 2406.06512 • Published • 2
MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders
Paper • 2502.14753 • Published • 1
SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning
Paper • 2506.21355 • Published • 10
Expert-level validation of AI-generated medical text with scalable language models
Paper • 2507.03152 • Published
Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data
Paper • 2508.16783 • Published • 1
ryanramos
authored a
paper 7 months ago
mbrack
authored a
paper 9 months ago
mbrack
authored 3
papers 10 months ago
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Paper • 2303.09289 • Published • 2
Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
Paper • 2309.11575 • Published
MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
Paper • 2305.15296 • Published • 1