Yiyang Fang (方羿阳)

PhD · Department of Computer Science and Engineering, HKUST

I am a Ph.D. student in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), advised by Prof. Yi R. (May) Fung. I received my master's degree from the School of Computer Science at Wuhan University in 2026, under the supervision of Prof. Mang Ye. I received my bachelor's degree from the School of Computer Science and Technology at Shandong University in 2024.

My research mainly focuses on Multimodal Emotion Recognition and Multimodal Large Language Models. If you are interested in collaborating with me, feel free to contact me via email.

News

  • 2026.07 Switch-Reasoner was available as a preprint on arXiv.
  • 2026.06 Graduated from Wuhan University.
  • 2026.05 One paper was accepted to ICML 2026.
  • 2026.02 Two papers were accepted to CVPR 2026 and selected as Highlights.
  • 2025.05 SEPM was accepted to ICML 2025 as a Spotlight paper.
  • 2025.02 EMOE was accepted to CVPR 2025, see you in Nashville.

Research Interests

Multimodal Emotion Recognition

Understanding emotional cues across visual, textual, and multimodal signals.

Multimodal Large Language Models

Improving perception, reasoning, and adaptation in multimodal foundation models.

Publications (Selected)

† equal contribution

Switch-Reasoner thumbnail

Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning

Preprint

Yiyang Fang, Pei Fu, Jinjie Li, Jian Liang, Wenke Huang, Ruijie Luo, Shaojie Zhang, Jian Luan, Yi R. Fung, Mang Ye

Preprint
EMO-R3 thumbnail

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models

CVPR26 Highlight

Yiyang Fang, Wenke Huang, Pei Fu, Yihao Yang, Kehua Su, Zhenbo Luo, Jian Luan, Mang Ye

Paper Project Page
SEPM thumbnail

Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models

ICML25 Spotlight

Yiyang Fang, Jian Liang, Wenke Huang, He Li, Kehua Su, Mang Ye

Paper Project Page
EMOE thumbnail

EMOE: Modality-Specific Enhanced Dynamic Emotion Experts

CVPR25

Yiyang Fang, Wenke Huang, Guancheng Wan, Kehua Su, Mang Ye

Paper Project Page
MLLM tuning thumbnail

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

Preprint

Wenke Huang, Jian Liang, Xianda Guo, Yiyang Fang†, Guancheng Wan, Xuankun Rong, Chi Wen, Zekun Shi, Qingyun Li, Didi Zhu, Yanbiao Ma, Ke Liang, Bin Yang, He Li, Jiawei Shao, Mang Ye, Bo Du

Preprint

Academic Service

  • Reviewer for CVPR 2026, NeurIPS 2026, ECCV 2026 and AAAI 2027.
  • Reviewer for IEEE TIP and IEEE TIFS.

Education

  • Wuhan University

    Master Student, School of Computer Science

    2024.09 - 2026.06
  • Shandong University

    Bachelor, School of Computer Science and Technology

    2020.09 - 2024.06