Shaofeng Yin (殷绍峰)

I'm a senior undergraduate student at Peking University, majoring in artificial intelligence (Zhi Class). In Spring 2025, I visited Berkeley AI Research and had a wonderful time there.

My early research focused on human-object interaction detection (HOID) in computer vision. As vision-language models (VLMs) have grown impressively powerful, I've become deeply interested in the study of multimodal agents.

In my life, I have a deep appreciation for art, literature, and philosophy. I'm also deeply commited to volunteer teaching programs. I was passionate about competitive programming and earned the title of Codeforces Master at the age of 15.

Email  /  Scholar  /  Linkedin  /  Github

📚 Selected Publications

Vision-as-inverse-graphics, the concept of reconstructing an image as an editable graphics program is a long-standing goal of computer vision. Yet even strong VLMs aren't able to achieve this in one-shot as they lack fine-grained spatial and physical grounding capability. Our key insight is that closing this gap requires interleaved multimodal reasoning through iterative execution and verification. Stemming from this, we present VIGA (Vision-as-Inverse-Graphic Agent) that starts from an empty world and reconstructs or edits scenes through a closed-loop write-run-render-compare-revise procedure.

Recent benchmarks reveal significant gaps in real-world tool-use proficiency, particularly in functionally diverse multimodal settings requiring multi-step reasoning. To bridge this gap, we propose ToolEngine, a novel data generation pipeline that employs Depth-First Search (DFS) with a dynamic in-context example matching mechanism to simulate human-like tool-use reasoning.

🏆 Selected Awards

📸 Selected Photography

The template is stole from Jon Barron.