collaborators

12 papers

cs.CV2026

The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering

Yuqian Fu, Tianwen Qian, Yanjun Li +30

EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scena…

cs.CV2026

The Right Inference Strategy Is All You Need: Nearly Training-Free Domain-Wise Inference for EgoCross Challenge

Leyi Wu, Yifan Zhao, Jinjie Zhang +2

EgoCross evaluates multimodal large language models on egocentric video question answering under substantial domain shift, where test videos come from surgery, industrial assembly,…

cs.CV2026

RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes

Leyi Wu, Yifan Zhao, Jinjie Zhang +11

Vision-Language Models (VLMs) have shown strong visual understanding and are increasingly deployed in embodied AI systems, where reliable perception under real conditions is essent…

cs.CV2026

AnimationBench: Are Video Models Good at Character-Centric Animation?

Leyi Wu, Pengjun Fang, Kai Sun +8

Video generation has advanced rapidly, with recent methods producing increasingly convincing animated results. However, existing benchmarks-largely designed for realistic videos-st…

cs.CV2026

Motion Dreamer: Boundary Conditional Motion Reasoning for Physically Coherent Video Generation

Tianshuo Xu, Zhifei Chen, Leyi Wu +5

Recent advances in video generation have shown promise for generating future scenarios, critical for planning and control in autonomous driving and embodied intelligence. However,…

cs.CV2026

Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics

Tianshuo Xu, Zhifei Chen, Leyi Wu +2

The ultimate goal of video generation is to satisfy a fundamental trilemma: achieving high visual quality, maintaining rigorous physical consistency, and enabling precise controlla…