news

May 18, 2026 Joined Futurewei Technologies, Inc. as a Research Intern, Generative AI & World Modeling (Full-time).
May 13, 2026 🎉 Releasing PhyGround (first author) — a benchmark for the physical plausibility of image-to-video generation: 250 physics-aware prompts, 8 ti2v models scored on 3 general + 13 physical-law rubrics, plus a human-aligned judge model. Paper: arXiv Dataset: HuggingFace Code: GitHub.
May 13, 2026 A Very Big Video Reasoning Suite is accepted by ICML 2026! Paper:A Very Big Video Reasoning Suite (co-first author) Dataset: HuggingFace Code: GitHub.