Bowen Pan (潘柏文)

  • Ph.D. student in Computer Science
  • Massachusetts Institute of Technology
  • Email: bpan[at]mit.edu

    •        

    I am a final-year PhD student at MIT CSAIL. I'm very fortunate to be advised by Dr. Aude Oliva. I also work closely with Prof. Yoon Kim. Previously I obtained my bachelor’s degree in Electronic Engineering from Shanghai Jiao Tong University in 2019.
    My research focuses on efficient AI agents, specifically:
    • Generalization efficieny: Multimodal LLM agents with synthetic data
    • Computation efficiency: (1) Efficient image and video transformers, and (2) Memory efficient Mixture-of-Experts models

    Publications

    *: equal contribution
    Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models
    Bowen Pan, Yikang Shen, Haokun Liu, Mayank Mishra, Gaoyuan Zhang, Aude Oliva, Colin Raffel, Rameswar Panda
    arXiv 2024  paper / blog
    LangNav: Language as a Perceptual Representation for Navigation
    Bowen Pan, Rameswar Panda, SouYoung Jin, Rogerio Feris, Aude Oliva, Phillip Isola, Yoon Kim
    NAACL 2024  paper / code / model / MIT News
    HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World
    Xin Wang*, Taein Kwon*, Mahdi Rad, Bowen Pan, Ishani Chakraborty, Sean Andrist, Dan Bohus, Ashley Feniello, Bugra Tekin, Felipe Vieira Frujeri, Neel Joshi, Marc Pollefeys
    ICCV 2023  paper / code / datasets / challenges
    Egocentric Vision 2022/2023 Distinguished Paper Award
    Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding
    Mathew Monfort, Bowen Pan, Kandan Ramakrishnan, Alex Andonian, Barry A McNamara, Alex Lascelles, Quanfu Fan, Dan Gutfreund, Rogerio Feris, Aude Oliva
    TPAMI 2021  paper / datasets / challenges
    Argoverse 2.0: Next Generation Datasets for Self-Driving Perception and Forecasting
    Benjamin Wilson, William Qi, Tanmay Agarwal, John Lambert, Jagjeet Singh, Siddhesh Khandelwal, Bowen Pan, Ratnesh Kumar, Andrew Hartnett, Jhony Kaesemodel Pontes, Deva Ramanan, Peter Carr, James Hays
    NeurIPS 2021 (Track on Datasets and Benchmarks)  paper / code / datasets / project page
    IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformer
    Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang, Rogerio Feris, Aude Oliva
    NeurIPS 2021  paper / demo / project page
    VA-RED2: Video Adaptive Redundancy Reduction
    Bowen Pan, Rameswar Panda, Camilo Fosco, Chung-Ching Lin, Alex Andonian, Yue Meng, Kate Saenko, Aude Oliva, Rogerio Feris
    ICLR 2021  paper / project page
    Cross-view Semantic Segmentation for Sensing Surroundings
    Bowen Pan*, Jiankai Sun*, Ho Yin Tiga Leung, Alex Andonian, Bolei Zhou
    RA-L and IROS 2020  paper / code / demo
    Oral Presentation
    Recurrent Residual Module for Fast Inference in Videos
    Bowen Pan, Wuwei Lin, Xiaolin Fang, Chaoqin Huang, Bolei Zhou, Cewu Lu
    CVPR 2018  paper

    Professional Services

  • Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, AAAI
  • Journal Reviewer: TPAMI, TRO, RA-L

    • Misc

  • In my spare time, I play soccer and was fortunate to meet a great group of soccer buddies during my PhD at Cambridge. We participated in the MIT Intramural (Beaver Cup) and reached the semifinals in the 2023-2024 season.


    • Bowen Pan