👋 Hi!

I am Chufan Shi, a second-year PhD student from at University of Southern California, fortunately advised by Prof. Xuezhe Ma.

Prior to USC, I earned my master’s degree from Tsinghua University, advised by Prof. Yujiu Yang and bachelor’s degree from University of Electronic Science and Technology of China.

Currently, I am interested in LLM Pre-Training and (M)LLM Post-Training.

Snipaste_2026-06-26_16-12-46.png

Email Twitter

📜 Publications

Listed are my first and co-first author papers; see my Google Scholar profile for the full list.

image.png

Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination

Chufan Shi, Cheng Yang, Yaokang Wu, Linhao Jin, Bo Shui, Taylor Berg-Kirkpatrick, Xuezhe Ma

ICML 2026 Oral [paper][code]

image.png

Snipaste_2026-06-26_16-39-48.png

Snipaste_2026-06-26_16-22-05.png

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

Xin Gao, Cheng Yang, Chufan Shi, Taylor Berg-Kirkpatrick

ICML 2026 [paper][code]

Ureason: Benchmarking the reasoning paradox in unified multimodal models

Cheng Yang, Chufan Shi, Bo Shui, Yaokang Wu, Muzi Tao, Huijuan Wang, Ivan Yee Lee, Yong Liu, Xuezhe Ma, Taylor Berg-Kirkpatrick

Preprint [paper][code]

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning

Ruilin Luo, Chufan Shi, Yizhen Zhang, Cheng Yang, Songtao Jiang, Tongkun Guan, Ruizhe Chen, Ruihang Chu, Peng Wang, Mingkun Yang, Lei Wang, Yujiu Yang, Junyang Lin, Zhibo Yang

ICLR 2026 [paper][code]

image.png

ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation

Chufan Shi, Cheng Yang, Yaxin Liu, Bo Shui, Junjie Wang, Mohan Jing, Linran Xu, Xinyu Zhu, Siheng Li, Yuxiang Zhang, Gongye Liu, Xiaomei Nie, Deng Cai, Yujiu Yang

ICLR 2025 [paper][code]

image.png

LLM2: Let Large Language Models Harness System 2 Reasoning

Cheng Yang, Chufan Shi, Siheng Li, Bo Shui, Yujiu Yang, Wai Lam NAACL 2025 [paper][code]

image.png

Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast

Chufan Shi, Cheng Yang, Xinyu Zhu, Jiahao Wang, Taiqiang Wu, Siheng Li, Deng Cai, Yujiu Yang, Yu Meng

NeurIPS 2024 [paper][code]

Snipaste_2026-06-26_16-28-45.png

Snipaste_2026-06-26_16-35-24.png

Snipaste_2026-06-26_16-34-44.png

A Thorough Examination of Decoding Methods in the Era of LLMs

Chufan Shi, Haoran Yang, Deng Cai, Zhisong Zhang, Yifan Wang, Yujiu Yang, Wai Lam

EMNLP 2024 [paper][code]

Specialist or Generalist? Instruction Tuning for Specific NLP Tasks

Chufan Shi, Yixuan Su, Cheng Yang, Yujiu Yang, Deng Cai

EMNLP 2023 [paper][code]

LiFi: Lightweight Controlled Text Generation with Fine-Grained Control Codes

Chufan Shi, Deng Cai, Yujiu Yang

Preprint [paper]

👨‍💻Research Internships