Yake Wei

Yake Wei's research focuses primarily on multimodal perception and learning mechanisms. She has published more than ten papers in top-tier artificial intelligence journals and conferences, including TPAMI, NeurIPS, ICML, and CVPR, with multiple papers selected for oral presentation at NeurIPS and CVPR. Representative works include OGM, a balanced multimodal learning algorithm designed to improve the effective utilization of heterogeneous multimodal information, and MokA, a parameter-efficient fine-tuning method for multimodal large language models that builds on modality-specific characteristics. She was selected for the CVPR Doctoral Consortium and has received honors including the Baidu Scholarship and the Wu Yuzhang Scholarship of Renmin University of China. She also regularly serves as a reviewer for journals and conferences including TPAMI, NeurIPS, ICML, and CVPR.

Enter Personal Website

Education

2021–2026, Ph.D., Renmin University of China

2017–2021, B.E., University of Electronic Science and Technology of China

Research Interests

External Perception & Cognition. Advancing the perception and cognition ability of multimodal intelligence to support coherent understanding, reasoning, and interaction across complex physical and digital environments.

Internal Learning Dynamics. Leveraging cognitive neuroscience and mathematical tools to investigate the coordination, integration, and interaction of heterogeneous multimodal information within unified learning systems.

Teaching

Undergraduate course: Programming

Publications

For more information, visit: https://echo0409.github.io/

Information-Theoretic Decomposition for Multimodal Interaction Learning

Zequn Yang, Yake Wei, Haotian Ni, Zhihao Xu, Di Hu

CVPR, 2026

MokA: Multimodal Low-Rank Adaptation for MLLMs

Yake Wei, Yu Miao, Dongzhan Zhou, Di Hu

NeurIPS (Oral Presentation), 2025

RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer

Haotian Ni, Yake Wei, Hang Liu, Gong Chen, Chong Peng, Hao Lin, Di Hu

ICML, 2025

Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition

Chengxiang Huang*, Yake Wei*, Zequn Yang, Di Hu

CVPR, 2025

Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception

Ruotian Peng, Haiying He, Yake Wei, Yandong Wen, Di Hu

CVPR, 2025

On-the-fly Modulation for Balanced Multimodal Learning

Yake Wei, Di Hu, Henghui Du, Ji-Rong Wen

T-PAMI, 2024

Diagnosing and Re-learning for Balanced Multimodal Learning

Yake Wei, Siwei Li, Ruoxuan Feng, Di Hu

ECCV, 2024

MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance

Yake Wei, Di Hu

ICML, 2024

Enhancing Multimodal Cooperation via Sample-level Modality Valuation

Yake Wei, Ruoxuan Feng, Zihe Wang, Di Hu

CVPR, 2024

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

Zequn Yang, Yake Wei, Ce Liang, Di Hu

ICLR, 2024

Geometric-inspired graph-based Incomplete Multi-view Clustering

Zequn Yang, Han Zhang, Yake Wei, Zheng Wang, Feiping Nie, Di Hu

Pattern Recognition, 2023

Balanced Multimodal Learning via On-the-fly Gradient Modulation

Xiaokang Peng*, Yake Wei*, Andong Deng, Dong Wang, Di Hu

CVPR (Oral Presentation), 2022

Learning to Answer Questions in Dynamic Audio-Visual Scenarios

Guangyao Li*, Yake Wei*, Yapeng Tian*, Chenliang Xu, Ji-Rong Wen, Di Hu

CVPR (Oral Presentation), 2022

Class-aware Sounding Objects Localization via Audiovisual Correspondence

Di Hu, Yake Wei, Rui Qian, Weiyao Lin, Ruihua Song, Ji-Rong Wen

T-PAMI, 2021

Contact

Email: yakewei@ruc.edu.cn

Personal homepage: https://echo0409.github.io/