News Archive

A full record of papers, talks, milestones, and press since 2022. Same content as the homepage highlights, organized by year.

2026
2025
  • Dec 2025PaperOne paper accepted by IEEE TIP.
  • Dec 2025TalkI give an oral presentation at NeurIPS 2025 about Benchmarking Reasoning-Informed Visual Editing. Slides.
  • Oct 2025PaperVideo-MMLU received the Outstanding Paper Award at ICCV 2025 Workshop @ Knowledge-Intensive Multimodal Reasoning with Travel Grant.
  • Sep 2025PaperOne paper accepted by NeurIPS 2025, two papers accepted by NeurIPS 2025 Datasets and Benchmarks Track with one Oral.
  • Sep 2025RoleWe receive the Lambda Research Grant $5,000 to support our research.
  • Sep 2025PaperOne paper accepted by ICCV 2025 Workshop @ Knowledge-Intensive Multimodal Reasoning.
  • Sep 2025TalkInvited talk at Abaka AI and 2077AI titled Better and Longer Video Understanding. Slides.
  • Sep 2025MilestoneJoin Princeton University as a CS Ph.D. student.
  • Aug 2025PaperOne paper accepted by IEEE TPAMI.
  • Aug 2025TalkLiveCodeBench Pro presented in Open AGI Symposium at University of California, Berkeley. Slides.
  • Jul 2025PressInterviewed by DeepTech and MIT Technology Review China. Post.
  • Jul 2025PaperTwo papers accepted by ICCV 2025 Workshop @ Findings.
  • Jun 2025PaperOne paper accepted by ICCV 2025.
  • Jun 2025PressFeatured in MIT Technology Review as one of the lead authors of LiveCodeBench Pro.
  • Jun 2025PaperOne paper accepted by IROS 2025.
  • May 2025PaperOne paper accepted by ACL 2025.
  • May 2025PaperTwo papers accepted by CVPR 2025 Workshop @ 3D LLM/VLA.
  • Apr 2025EventWe host CVPR 2025 Video Understanding Challenge @ LOVEU sponsored by Lambda.
  • Apr 2025PaperOne paper accepted by CVPR 2025 Workshop @ Urban Scene Modeling.
  • Mar 2025PaperOne paper accepted by CVPR 2025 Workshop @ Efficient Large Vision Models.
  • Mar 2025PaperOne paper accepted by IEEE TVCG.
  • Mar 2025MilestoneGraduated from the University of Washington with a Master's thesis on Large Multimodal Models for Video Captioning, nominated for the Distinguished Thesis Award by the ECE Department.
  • Feb 2025PaperThree papers accepted by CVPR 2025.
  • Jan 2025PaperTwo papers accepted by ICLR 2025.
2024
  • Dec 2024PaperOne paper accepted by ICASSP 2025 as Lecture (Oral).
  • Jul 2024PaperTwo papers accepted by ECCV 2024.
  • Jun 2024PaperOne technique report accepted by CVPR 2024 Workshop @ NTIRE.
  • Jun 2024RoleI work with Pika Labs as intern to develop next-generation video understanding and generation models.
  • Apr 2024EventWe host CVPR 2024 Long-form Video Understanding Challenge @ LOVEU.
  • Apr 2024TalkInvited talk at AgentX seminar about our STEVE series works.
  • Mar 2024PaperOne paper accepted by ICLR 2024 Workshop @ LLM Agents.
  • Feb 2024PaperTwo papers accepted by CVPR 2024 with one highlight (2.81%).
  • Feb 2024TalkInvited talk at AAAI 2024 Workshop @ IMAGEOMICS.
2023
  • Dec 2023PaperOne paper accepted by AAAI 2024.
  • Nov 2023PaperOne paper accepted by WACV 2024.
  • Sep 2023PaperOne paper accepted by IEEE TMM.
  • Aug 2023PaperOne paper accepted by BMVC 2023.
  • Jul 2023PaperTwo papers accepted by ACM MM 2023.
  • Jul 2023PaperTwo papers accepted by ICCV 2023.
  • Jun 2023MilestoneI graduate from Zhejiang University with Bachelor's degree.
  • Apr 2023PaperOne paper accepted by CVPR 2023 Workshop @ Computer Vision for Fashion, Art, and Design.
  • Mar 2023PaperOne paper accepted by IEEE TAI.
  • Mar 2023MilestoneI become a graduate student member of Information Processing Lab at University of Washington, advised by Professor Jenq-Neng Hwang.
  • Feb 2023RoleI become a research intern at Microsoft Research Asia (MSRA), advised by principal researcher Xun Guo.
2022
  • Sep 2022PaperOne paper accepted by ICTAI 2022.
  • Jul 2022MilestoneBecome a member of National Center for Supercomputing Applications (NCSA) at University of Illinois Urbana-Champaign, work with Professor Volodymyr (Vlad) Kindratenko.
  • Jun 2022PaperOne paper accepted by Applied Science.
  • Jan 2022MilestoneStart doing research with Professor Gaoang Wang.