SHAOFENG
profile photo

Shaofeng Zhang

I am a fourth-year Ph.D student at Shanghai Jiao Tong University, Shanghai. I am supervised by Professor Junchi Yan and Hongyuan Zha. I mainly work on self-supervised learning, diffusion, and graph neural networks, etc. Before that, I did my bachelor at University of Electronic and Science and Technology of China.

Email  /  Google Scholar  /  DBLP

News

  • 09/2024, One paper accepted to NeurIPS 2024.
  • 01/2024, One paper accepted to ICLR 2024.
  • 04/2023, One paper accepted to ICML 2023.
  • 01/2023, Two papers accepted to ICLR 2023.
  • 07/2022, One paper accepted to ECCV 2022.
  • Research

    First-author & Co-first author paper

    1. PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
      Xiangdong Zhang*, Shaofeng Zhang*, Junchi Yan
      NeurIPS 2024 Spotlight (* equal contribution) | Paper | Code

    2. Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
      Shaofeng Zhang, Jinfa Huang, Qiang Zhou, Zhibin Wang, Fan Wang, Jiebo Luo, Junchi Yan
      ICLR 2024 | Paper | Code

    3. Patch-level Contrastive Learning via Positional Query for Visual Pre-training
      Shaofeng Zhang, Qiang Zhou, Zhibin Wang, Fan Wang, Junchi Yan
      ICML 2023 | Paper | Code

    4. Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
      Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan
      ICLR 2023 | Paper | Code

    5. Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual Pretraining
      Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan
      ICLR 2023 | Paper | Code

    6. Self-supervised Learning of Visual Graph Matching
      Chang Liu*, Shaofeng Zhang*, Junchi Yan, Xiaokang Yang
      ECCV 2022 (* equal contribution) | Paper | Code

    7. M-Mix: Generating Hard Negatives via Multi-sample Mixing for Contrastive Learning
      Shaofeng Zhang, Meng Liu, Junchi Yan, Hengrui Zhang, Lingxiao Huang, Pinyan Lu, Xiaokang Yang
      KDD 2022 Oral | Paper | Code

    8. Align Representations with Base: A New Approach to Self-Supervised Learning
      Shaofeng Zhang, Lyn Qiu, Feng Zhu, Junchi Yan, Hengrui Zhang, Rui Zhao, Hongyang Li, Xiaokang Yang
      CVPR 2022 | Paper | Code

    9. Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning
      Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang
      ICLR 2022 | Paper | Code

    10. The Diversified Ensemble Neural Network
      Shaofeng Zhang, Meng Liu, Junchi Yan
      NeurIPS 2020 | Paper

    11. Fooled by Imagination: Adversarial Attack to Image Captioning Via Perturbation in Complex Domain
      Shaofeng Zhang*, Zheng Wang*, Xing Xu, Xiang Guan, Yang Yang
      ICME 2020 Oral (* equal contribution) | Paper

    Co-authored paper:

    1. HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
      Junkun Yuan, Xinyu Zhang, Hao Zhou, Jian Wang, Zhongwei Qiu, Zhiyin Shao, Shaofeng Zhang, Sifan Long, Kun Kuang, Kun Yao, Junyu Han, Errui Ding, Lanfen Lin, Fei Wu, Jingdong Wang
      NeurIPS 2023

    2. Localized contrastive learning on graphs
      Hengrui Zhang, Qitian Wu, Yu Wang, Shaofeng Zhang, Junchi Yan, Philip S Yu
      arXiv:2212.04604

    3. Revo-lion: Evaluating and refining vision-language instruction tuning datasets
      Ning Liao, Shaofeng Zhang, Renqiu Xia, Bo Zhang, Min Cao, Yu Qiao, Junchi Yan
      arXiv:2310.06594

    4. Regionblip: A unified multi-modal pre-training framework for holistic and regional comprehension
      Qiang Zhou, Chaohui Yu, Shaofeng Zhang, Sitong Wu, Zhibing Wang, Fan Wang
      arXiv:2308.02299

    5. ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
      Shenghai Yuan, Jinfa Huang, Yongqi Xu, Yaoyang Liu, Shaofeng Zhang, Yujun Shi, Ruijie Zhu, Xinhua Cheng, Jiebo Luo, Li Yuan
      NeurIPS 2024 D&B Track Spotlight

    6. Motion Control for Enhanced Complex Action Video Generation
      Qiang Zhou, Shaofeng Zhang, Nianzu Yang, Ye Qian, Hao Li
      arXiv:2411.08328

    Working Experience

  • Research intern at Sensetime Research. (Jul. 2021 to Oct. 2022)
    Explore the representation learning and general self-supervised learning.
  • Research intern at Tencent. (Feb. 2021 to May. 2021)
    Worked on improving the generalization ability of unsupervised classification and detection.
  • Research intern at SmartMore. (Jul. 2020 to Sep. 2020)
    Worked on general represetantion learning.
  • Research intern at Microsoft Research. (Jan. 2020 to Jul. 2020)
    Contributed to the AI education book, github project and video.
  • Services

  • PC member/Reviewer: CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML.