June 2025: Evaluation Agent was selected for an oral presentation and SAC Highlight Award (43/8350) at ACL 2025.
May 2025: Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning was released. Code and data can be found here.
May 2025: MMInA leaderboard is now live.
May 2025: Two papers accepted to ACL 2025 (one main and one findings).
March 2025: Acknowledged as an outstanding reviewer for ICLR 2025 [SCOPE Workshop].
January 2025: Paper 'AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation' accepted to ICLR 2025.
December 2024: Paper 'Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models' released.
April 2024: Paper 'MMInA: Benchmarking Multihop Multimodal Internet Agents' released.
June 2023: Paper 'Enhancing Low-Light Images Using Infrared-Encoded Images' accepted to ICIP 2023.
Background
Research interests include vision-language model reasoning, low-light image enhancement, etc. Currently pursuing a PhD at Nanyang Technological University, Singapore, under the supervision of Prof. Ziwei Liu and Dr. Hongyuan Zhu.
Miscellany
Music: Piano & Electrical Keyboard (highest level), certified by China Musicians Association; Fingerstyle guitar (fan of Masaaki Kishibe). Sports: Diving (PADI certified Open Water and Advanced Open Water Diver), badminton, hiking, etc.