Yang Shi
Yang Shi's profile picture

Yang Shi

Master's Student

Peking University

sudo.shiyang@gmail.com

About Yang Shi

I am a master's student in the School of Electronic and Computer Engineering at Peking University, advised by Prof. Ge Li. My research centers on computer vision, multimodal learning, and world models.

I study intelligence beyond perceptual fidelity: how models can preserve the distinctions that matter for prediction, counterfactual reasoning, and action. I am particularly interested in building compact, revisable world models that integrate language, vision, and action as partial evidence about an evolving reality, enabling reliable reasoning and intervention under uncertainty.

News

  1. Two papers were accepted to ACMMM 2026.

  2. ChordEdit received the CVPR 2026 Best Student Paper Honorable Mention.

  3. One paper was accepted to SIGKDD 2026.

  4. One paper was accepted to ICML 2026.

  5. One paper was accepted to ACL 2026 (Main).

  6. One paper was accepted to CVPR 2026.

  7. One paper was accepted to WWW 2026.

  8. Received funding from the National College Students' Innovation and Entrepreneurship Program.

Education

–

Guangdong University of Technology

School of Computer Science

–

Peking University

School of Electronic and Computer Engineering

Selected Publications

* Equal contribution · † Corresponding author

View All Publications

Diffusion Image Editing via Asynchronous Token Decoding

Yang Shi, Liangsi Lu†, Minzhe Guo, Yifeng Xie, Yanhui Chen, Jingchao Wang, Xuhang Chen

ACMMM 2026

Semantic Granularity Navigation in Image Editing

Liangsi Lu, Minzhe Guo, Xuhang Chen, Yang Shi†

ICML 2026

MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models

Yang Shi, Yifeng Xie, Minzhe Guo, Liangsi Lu, Mingxuan Huang, Jingchao Wang, Zhihong Zhu, Boyan Xu†, Zhiqi Huang

ACL 2026 (Main)

ChordEdit: One-Step Low-Energy Transport for Image Editing

Liangsi Lu, Xuhang Chen, Minzhe Guo, Shichu Li, Jingchao Wang, Yang Shi†

CVPR 2026 Best Student Paper Honorable Mention

Award