ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks Paper • 2603.27862 • Published Mar 29 • 33
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction Paper • 2602.13294 • Published Feb 9 • 13
Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs Paper • 2602.01600 • Published Feb 2 • 21
TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding Paper • 2502.19400 • Published Feb 26, 2025 • 47
