Sihan Yang

I am currently a final-year undergraduate student at the University of Electronic Science and Technology of China. I will be joining The Chinese University of Hong Kong as a PhD student in Fall 2026. Previously, I had a wonderful experience as a research intern at Shanghai AI Laboratory.

Email / CV / Scholar / Github

Research

I'm interested in network architecture for foundation models, efficient deep learning and spatial intelligence. Some papers are highlighted.

^*Equal Contribution ^‡Project Lead ^†Corresponding Author

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
Sihan Yang^*, Runsen Xu^*‡, Yiman Xie, Sizhe Yang, Mo Li, Jingli Lin, Chenming Zhu, Xiaochen Chen, Haodong Duan, Xiangyu Yue, Dahua Lin, Tai Wang^†, Jiangmiao Pang^†
arXiv
Homepage | Dataset | Paper | arXiv

We introduce a challenging, diverse, and comprehensive multi-image spatial reasoning benchmark, manually annotated by six 3D vision experts, which additionally supports thorough evaluation of reasoning processes.

VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization
Sihan Yang, Runsen Xu, Chenhang Cui, Tai Wang, Dahua Lin, Jiangmiao Pang
ICCV 2025
Paper | arXiv | Code

We propose a visual token pruning framework that designs optimal, model-specific pruning strategies for different MLLMs.

Improving Alignment in LVLMs with Debiased Self-Judgment
Sihan Yang^*, Chenhang Cui^*, Zihao Zhao, Yiyang Zhou, Weilong Yan, Ying Wei, Huaxiu Yao
EMNLP 2025 Findings
Paper | arXiv | Dataset | Code

MLLMs achieve self-improvement at both test time and during training through their linguistic bias-removing self-judgment mechanism.

Miscellanea

Honors and Awards

SenseTime Scholarship (awarded annually to 30 UGs in the field of AI from across China)
National Scholarship for 2023/2024 Academic Year
National Scholarship for 2022/2023 Academic Year