Chen Wei

Hello! I am an Assistant Professor of Computer Science at Rice University (start Fall 2025), and a postdoctoral researcher at FAIR, Meta.

I completed my Ph.D. in Computer Science at Johns Hopkins University, advised by Bloomberg Distinguished Professor Alan L. Yuille. During my PhD study, I also interned at Google DeepMind. Before Hopkins, I received my B.S. with honors from Peking University.

I'm recruiting PhD students starting in Fall 2025. See instructions on applying below.

 /   /   /  weichen3012[at]gmail.com

profile photo
Research Interest
My primary areas of interest in research are computer vision and machine learning. Most of our understanding of the world stems from interpreting complex sensory signals, particularly visual information, yet turning this raw data into meaningful knowledge remains a fundamental challenge in artificial intelligence. My research aims to develop visual intelligence that can perceive, process and reason about visual signals with generality and scalability.
Lab Openings
I seek highly motivated candidates with strong technical backgrounds in AI/ML who share our passion for advancing visual intelligence, particularly through the following three directions:
  • Generative Understanding: Constructing and learning from generative models of the world.
  • Multimodal Learning: Connecting visual representations to commonsense knowledge base like LLMs to achieve higher-order cognition.
  • Self-Supervised Learning: Discovering structures in raw data to obtain scalable structured representations in wide domains of images and videos, and applicable to a variety of tasks.
  • 2025 Fall PhD Applicants: Please submit your application to the Rice CS PhD program, due Jan. 1, 2025 with no application fee, and mention me as one of your Faculty of Interest. While I will review all relevant applications, contacting me after submission through email can help flag your application.

    Rice Students: If you are a Rice student looking for potential advisors, please email me directly.

    Publications Selected / All

    Research Topics: Generative Understanding / Multimodal Learning / Self-Supervised Learning

    (* indicates equal contribution)

    De-Diffusion Makes Text a Strong Cross-Modal Interface
    Chen Wei, Chenxi Liu, Siyuan Qiao, Zhishuai Zhang, Alan Yuille, Jiahui Yu
    CVPR, 2024
    arXiv / project page
    Towards Generalizable Tumor Synthesis
    Qi Chen, Xiaoxi Chen, Haorui Song, Alan Yuille, Zhiwei Xiong, Chen Wei, Zongwei Zhou
    CVPR, 2024
    arXiv / code
    Unleashing the Power of Visual Prompting at the Pixel Level
    Junyang Wu*, Xianhang Li*, Chen Wei, Huiyu Wang, Alan Yuille, Yuyin Zhou, Cihang Xie,
    TMLR, 2024
    arXiv / code
    Tuning LayerNorm in Attention: Towards Efficient MultiModal LLM Finetuning
    Bingchen Zhao*, Haoqin Tu*, Chen Wei, Jieru Mei, Cihang Xie,
    ICLR, 2024 Spotlight
    arXiv / huggingface
    Instruct2Attack: Language-Guided Semantic Adversarial Attacks
    Jiang Liu, Chen Wei, Yuxiang Guo, Heng Yu, Alan Yuille, Soheil Feizi, Chun Pong Lau, Rama Chellappa
    arXiv, 2023
    arXiv
    Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
    Haoqin Tu*, Bingchen Zhao*, Chen Wei, Cihang Xie,
    NeurIPS Instruction Workshop, 2023
    arXiv / code
    Diffusion Models as Masked Autoencoders
    Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, Huiyu Wang, Cihang Xie, Alan Yuille, Christoph Feichtenhofer
    ICCV, 2023
    arXiv / project page / Marktechpost
    SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training
    Yuanze Lin, Chen Wei, Huiyu Wang, Alan Yuille, Cihang Xie
    ICCV, 2023
    arXiv
    Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
    Chaitanya Ryali*, Yuan-Ting Hu*, Daniel Bolya*, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li*, Christoph Feichtenhofer*
    ICML, 2023 Oral
    arXiv / code
    Masked Autoencoders Enable Efficient Knowledge Distillers
    Yutong Bai, Zeyu Wang, Junfei Xiao, Chen Wei, Huiyu Wang, Alan Yuille, Yuyin Zhou, Cihang Xie
    CVPR, 2023
    arXiv / code
    CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation
    Feng Wang, Huiyu Wang, Chen Wei, Alan Yuille, Wei Shen
    ECCV, 2022
    arXiv / code
    In Defense of Image Pre-Training for Spatiotemporal Recognition
    Xianhang Li, Huiyu Wang, Chen Wei, Jieru Mei, Alan Yuille, Yuyin Zhou, Cihang Xie
    ECCV, 2022
    arXiv / code
    Masked Feature Prediction for Self-Supervised Visual Pre-Training
    Chen Wei*, Haoqi Fan, Saining Xie, Chao-Yuan Wu, Alan Yuille, Christoph Feichtenhofer*
    CVPR, 2022
    arXiv / code at pySlowFast

    Most Influential CVPR 2023 Papers
    iBOT: Image BERT Pre-Training with Online Tokenizer
    Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, Tao Kong
    ICLR, 2022
    arXiv / code / press


    Improved and scaled up to the foundation model DINOv2 by Meta AI.
    CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
    Chen Wei, Kihyuk Sohn, Clayton Mellina, Alan Yuille, Fan Yang
    CVPR, 2021
    arXiv / code / poster / video
    CO2: Consistent Contrast for Unsupervised Visual Representation Learning
    Chen Wei, Huiyu Wang, Wei Shen, Alan Yuille
    ICLR, 2021
    arXiv / Open Review / video
    Iterative Reorganization with Weak Spatial Constraints:
    Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning

    Chen Wei, Lingxi Xie, Xutong Ren, Yingda Xia, Chi Su, Jiaying Liu, Qi Tian, Alan Yuille
    CVPR, 2019
    arXiv / code
    Deep Retinex Decomposition for Low-Light Enhancement
    Chen Wei*, Wenjing Wang*, Wenhan Yang, Jiaying Liu
    BMVC, 2018 Oral
    arXiv / code / project page & dataset

    #2 Most Cited BMVC Papers Over the Last Five Years


    GLADNet: Low-Light Enhancement Network with Global Awareness
    Wenjing Wang*, Chen Wei*, Wenhan Yang, Jiaying Liu
    FG Workshop, 2018
    PDF / code / project page

    Last update: Nov. 2024      Template