Google Scholar / Github / Twitter

XuDong Frank Wang (王旭东)

Hi! I am a Ph.D. candidate in Berkeley AI Research (BAIR) lab at UC Berkeley, advised by Prof. Trevor Darrell. Prior to BAIR, I was a member of International Computer Science Institute (ICSI), advised by Prof. Stella X. Yu. I received my Master's Degree (thesis plan) in Intelligent Systems, Robotics and Control at University of California, San Diego, advised by Prof. Nuno Vasconcelos and Bachelor's Degree as an honorary member of Tang Aoqing Honors Program in Science at Jilin University.

I am currently a student researcher at Google DeepMind, working with Prof. Cordelia Schmid, Dr. Xingyi Zhou, and Dr. Alireza Fathi. Previously, I was a research scientist intern in the Generative AI Research (GenAI) team at Meta AI from May 2023 to Dec 2023, and before that, in Fundamental AI Research (FAIR) labs at Meta AI from May 2022 to Dec 2022. During my tenure at Meta, I had the privilege of collaborating with Dr. Ishan Misra and Dr. Rohit Girdhar. I also worked closely with Dr. Zhaowei Cai (Amazon AWS AI Labs), Dr. Zhirong Wu (Microsoft Research) and Prof. Ziwei Liu (NTU) from 2019 to 2022. I was a staff researcher at the vision group of ICSI between 2019 and 2020.

My research has been primarily focused on: [1] representation learning without reference to human annotations or under minimal human supervision. [2] text-to-image diffusion models. [3] grounded Large Multimodal Models (LMMs).

How to pronounce XuDong? It is composed of two syllables: "Xu" and "Dong": /ʃü/-/dɔ:ŋ/

Contact: xdwang [at] eecs [dot] berkeley [dot] edu

News

  • [11/2024] Delighted to be one of the Top Reviewers of NeurIPS 2024.

  • [10/2024] Unsupervised SAM is accepted by NeurIPS 2024!

  • [02/2024] InstanceDiffusion, VideoCutLER, U2Seg and SESAME are accepted by CVPR 2024!

  • [11/2023] Delighted to be one of the Top Reviewers of NeurIPS 2023!

  • [09/2023] HIPIE is accepted by NeurIPS 2023!

  • [02/2023] CutLER is accepted by CVPR 2023!

  • [07/2022] One paper is accepted by ECCV 2022!

  • [05/2022] Excited to start my internship at FAIR!

  • [03/2022] Three papers are accepted by CVPR 2022!

  • [05/2021] Delighted to have received the award for Outstanding Reviewer of CVPR 2021.

  • [02/2021] Two papers are accepted by CVPR 2021!

  • [01/2021] One paper is accepted by ICLR 2021 as the Spotlight Presentation!

  • [12/2020] The code of RIDE for long-tailed recognition is public avaliable!

  • [12/2020] The proposal of Xudong (project lead) is selected for the grant from the Center for Long-Term Cybersecurity.
    •

Publications & Preprints (*: equal contribution; †: project lead)

Visual Lexicon: Rich Image Features in Language Space
XuDong Wang, Xingyi Zhou, Alireza Fathi, Trevor Darrell, Cordelia Schmid
Tech report
[Preprint] [PDF]

SegLLM: Multi-round Reasoning Segmentation with Large Language Models
XuDong Wang*, Shaolun Zhang*, Shufan Li*, Konstantinos Kallidromitis, Kehan Li, Yusuke Kato, Kazuki Kozuka, Trevor Darrell
Tech report
[Project Page] [Preprint] [PDF]

Segment Anything without Supervision
XuDong Wang, Jingfeng Yang, Trevor Darrell
NeurIPS 2024
[Project Page] [Preprint] [PDF] Code

InstanceDiffusion: Instance-level Control for Image Generation
XuDong Wang, Trevor Darrell, Saketh Rambhatla, Rohit Girdhar, Ishan Misra
CVPR 2024
[Project Page] [Preprint] [PDF] Code

Rethinking Patch Dependence for Masked Autoencoders
Letian Fu, Long Lian, Renhao Wang, Baifeng Shi, XuDong Wang, Adam Yala, Trevor Darrell, Alexei A. Efros, Ken Goldberg
Tech Report
[Project Page] [Preprint] [PDF] Code

Unsupervised Universal Image Segmentation
Dantong Niu*†, XuDong Wang*†, Xinyang Han*, Long Lian, Roei Herzig, Trevor Darrell.
CVPR 2024
[Project Page] [Preprint] [PDF] Code

See, Say, and Segment: Teaching LMMs to Overcome False Premises
Tsung-Han Wu*, Giscard Biamby*, David Chan, Lisa Dunlap, Ritwik Gupta, XuDong Wang, Joseph E. Gonzalez, Trevor Darrell.
CVPR 2024
[Project Page] [Preprint] [PDF] Code

VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation
XuDong Wang, Ishan Misra, Ziyun Zeng, Rohit Girdhar and Trevor Darrell.
CVPR 2024
[Preprint] [BibTex] [PDF] Code

Hierarchical Open-vocabulary Universal Image Segmentation
XuDong Wang*, Shufan Li*, Konstantinos Kallidromitis*, Yusuke Kato, Kazuki Kozuka and Trevor Darrell.
NeurIPS 2023
[Project Page] [Preprint] [BibTex] [PDF] Code

Cut and Learn for Unsupervised Object Detection and Instance Segmentation
XuDong Wang, Rohit Girdhar, Stella X. Yu, Ishan Misra.
CVPR 2023
[Project Page] [Preprint] [BibTex] [PDF] Code

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning
XuDong Wang*, Long Lian*, Stella X. Yu.
ECCV 2022
[Preprint] [BibTex] [PDF] Code

Debiased Learning from Naturally Imbalanced Pseudo-Labels
XuDong Wang, Zhirong Wu, Long Lian, Stella X. Yu.
CVPR 2022
[Project Page] [Preprint] [BibTex] [PDF] Code

Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers
Yunhui Guo, XuDong Wang, Yubei Chen, Stella X. Yu.
CVPR 2022
[Preprint] [BibTex]

Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers
Tsung-Wei Ke, Jyh-Jing Hwang, Yunhui Guo, XuDong Wang, Stella X. Yu.
CVPR 2022 (Oral Presentation)
[Project Page] [Preprint] [BibTex] [PDF] Code

Unsupervised Visual Attention and Invariance for Reinforcement Learning
XuDong Wang*, Long Lian*, Stella X. Yu.
CVPR 2021
[Project Page] [Preprint] [BibTex] [PDF] Code

Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
XuDong Wang, Ziwei Liu, Stella X. Yu.
CVPR 2021
[Project Page] [Preprint] [BibTex] [PDF] Code

Long-tailed Recognition by Routing Diverse Distribution-Aware Experts.
XuDong Wang, Long Lian, Zhongqi Miao, Ziwei Liu, Stella X. Yu.
ICLR 2021 (Spotlight Presentation)
[Project Page] [Preprint] [BibTex] [PDF] Code

Volumetric Attention for 3D Medical Image Segmentation and Detection
XuDong Wang, Shizhong Han, Yunqiang Chen, Dashan Gao, Nuno Vasconcelos.
MICCAI 2019 (Early Accept)
[Preprint] [BibTex] [PDF]

Towards Universal Object Detection by Domain Attention
XuDong Wang, Zhaowei Cai, Dashan Gao, Nuno Vasconcelos.
CVPR 2019
[Project Page] [Preprint] [BibTex] [PDF] Code

Feature Space Transfer for Data Augmentation
Bo Liu, XuDong Wang, Mandar Dixit, Roland Kwitt, Nuno Vasconcelos.
CVPR 2018 (Oral Presentation)
[Preprint] [BibTex] [PDF] Code

Teaching

Teaching Assistant; CS 280: Computer Vision, Department of EECS, UC Berkeley, Spring 2022.

Instructors: Prof. Jitendra Malik and Prof. Stella X. Yu.

Teaching Assistant; CS 294-43: Large Scale Vision and Language Models, Department of EECS, UC Berkeley, Fall 2024.

Instructor: Prof. Trevor Darrell

Academic Services

  • Organizer of the 5th Workshop on Self-Supervised Learning - Theory and Practice at NeurIPS 2024.

  • Reviewer for CVPR (2019-now), ICCV (2021-now), ECCV (2022-now), NeurIPS (2022-now), ICML (2024-now), TPAMI, IJCV, JMLR, ACM ToG, TIP, etc.

    		•

    Masters/Undergraduate Students

    I am fortunate to collaborate with the following talented Masters/Undergraduate students:

  • Jingfeng Yang (Undergrads).

  • Shaolun Marlo Zhang (Undergrads).

  • Kehan Li (B.S. 2024). Next: M.S. student at Stanford

  • Ashish Pandian (B.S. 2024). Next: M.S. student at UC Berkeley

  • Xinyang Han (B.S. 2024). Next: Ph.D. student at UC Berkeley / UCSF

  • Shufan Li (B.S. 2023). Next: Ph.D. student at UCLA

  • Shaan Gill (B.S. 2023). Next: M.S. student at UC Berkeley

  • Long Tony Lian (B.S. 2022). Next: Ph.D. student at UC Berkeley

    		•

    Miscellaneous

    Coffee Shop Adventures. During my undergraduate years, I co-founded a coffee shop and lovingly furnished it from scratch with four friends. Owning a coffee shop that enabled me to connect, empathize, and deeply engage with numerous people touched my soul in ways words can hardly describe.

    As the Chief Editor of the Graduate Program Application Manual (in Chinese), I led a dedicated team of over 20 members, consisting of Chinese students studying in various countries. Our mission was to provide valuable insights and assistance to Chinese students who may not be familiar with the graduate program application process but aspire to explore educational opportunities abroad. Together, we created a comprehensive guide spanning more than 300 pages, available for free online! [Google Drive] Within this manual, we meticulously outlined the crucial steps for a successful application to graduate programs abroad. Moreover, we conducted insightful interviews with over 100 alumni, gathering their invaluable advice on seamlessly transitioning to a new country and charting promising career paths across various academic disciplines.

    Contact

    Email: xdwang [at] eecs [dot] berkeley [dot] edu