9 papers
APT: Atomic Physical Transitions for Causal Video-Language Understanding
Shang Wu, Haoran Lu, Songling Liu +7
Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as "bounce" can be correct while hiding the proc…
Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion
Haoran Lu, Shang Wu, Songling Liu +10
Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consiste…
Towards Sparse Video Understanding and Reasoning
Chenwei Xu, Zhen Ye, Shang Wu +8
We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA). Instead of uniformly sampling frames…
PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
Shang Wu, Chenwei Xu, Zhuofan Xia +6
State-of-the-art text-to-video (T2V) generators frequently violate physical laws despite high visual quality. We show this stems from insufficient physical constraints in prompts r…
Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies
Yibo Wen, Chenwei Xu, Jerry Yao-Chieh Hu +2
We present a three-stage framework for training deep learning models specializing in antibody sequence-structure co-design. We first pre-train a language model using millions of an…
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
Licheng Liu, Zihan Wang, Linjie Li +5
Multi-turn problem solving is critical yet challenging for Large Reasoning Models (LRMs) to reflect on their reasoning and revise from feedback. Existing Reinforcement Learning (RL…