6 citations · 9 across the 17 of their papers we have counts for
4 papers · 1 filter
APT: Atomic Physical Transitions for Causal Video-Language Understanding
Shang Wu, Haoran Lu, Songling Liu +6
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 +9
Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consiste…
PROGRESSLM: Towards Progress Reasoning in Vision-Language Models
Jianshu Zhang, Chengxuan Qian, Haosen Sun +4
Estimating task progress requires reasoning over long-horizon dynamics rather than recognizing static visual content. While modern Vision-Language Models (VLMs) excel at describing…
UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence
Ruihai Wu, Haoran Lu, Yiyan Wang +2
Garment manipulation (e.g., unfolding, folding and hanging clothes) is essential for future robots to accomplish home-assistant tasks, while highly challenging due to the diversity…