§ Hello, I'm

Bingchen Huang 黄炳琛

Algorithm Engineer · Meituan

I work on Multimodal Large Language Models and Continual Learning, with a long-standing interest in building intelligent visual systems that are continual and data-efficient. I received my M.Sc. from the FVL Lab, Fudan University, advised by Prof. Yu-Gang Jiang and Prof. Zhineng Chen, and my B.Eng. from East China University of Science and Technology.

Google Scholar GitHub LinkedIn CV (PDF)
Portrait of Bingchen Huang

§ 01 News

§ 02 Research Interests

Multimodal LLMs

Vision-language understanding, retrieval-augmented and in-context learning for large multimodal models.

Continual Learning

Class- and task-incremental learning that resists catastrophic forgetting under dynamic data streams.

Data-Efficient Vision

Few-shot and representation learning for robust visual systems with limited supervision.

§ 03 Publications

* denotes my contribution. Selected works below — see Google Scholar for the full list.

  1. arXiv 2025

    TDR: Task-Decoupled Retrieval with Fine-Grained LLM Feedback for In-Context Learning

    Yifu Chen, Bingchen Huang*, Zhiling Wang, Yuanchao Du, Junfeng Luo, Lei Shen, Zhineng Chen

    arXiv

  2. CVPR-W 2024

    NTIRE 2024 Quality Assessment of AI-Generated Content Challenge

    Xiaohong Liu, Xiongkuo Min, Guangtao Zhai, et al. (incl. Bingchen Huang*)

    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops

    arXiv

  3. ICCV 2023

    MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition

    Tianlun Zheng, Zhineng Chen, Bingchen Huang*, Wei Zhang, Yu-Gang Jiang

    IEEE/CVF International Conference on Computer Vision

    arXiv PDF Code

  4. AAAI 2023

    Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning

    Bingchen Huang*, Zhineng Chen, Peng Zhou, Jiayin Chen, Zuxuan Wu

    Proceedings of the AAAI Conference on Artificial Intelligence

    arXiv AAAI Code