Yang Shi
picture

Yang Shi

Undergraduate Student, School of Computer Science

Guangdong University of Technology

Computer Vision

sudo.shiyang@gmail.com Google Scholar

I am an undergraduate student at Guangdong University of Technology (expected 2027), focused on Computer Vision.

I study intelligence beyond perceptual fidelity. Intelligence is not the reproduction of ever finer multimodal detail, but the ability to preserve the distinctions that matter for how the world evolves and how actions change it. I view learning as predictive compression: forming compact, revisable beliefs that support prediction, counterfactual reasoning, and intervention. Language, vision, and action are partial evidence about one evolving reality; a world model should integrate this evidence not merely to generate plausible observations, but to reason and act reliably under uncertainty.

  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.

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 (CCF-A)

Semantic Granularity Navigation in Image Editing

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

ICML 2026 (CCF-A)

Project ArXiv

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 (CCF-A)

Project ArXiv Dataset Code

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

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

CVPR 2026 (CCF-A, Oral) Best Student Paper Honorable Mention

Project ArXiv Code Video Poster

Award