Weifeng Lin

3 papers The Chinese University of Hong Kong

• MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
• Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos
• UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents