Songyang Zhang

Young Researcher at Shanghai AI Laboratory, Shanghai, China.

zhangsongyang_1.jpeg

I am a Researcher of OpenMMLab, Shanghai AI Laboratory, supervised by Prof. Dahua Lin, collaborate with Dr. Kai Chen. I lead a team working on multi-modality model and large language model, includes the research and open-source platform. My team develops and maintains the OpenCompass, an evaluation platform for foundation model, and OpenMMLab projects MMPreTrain.

OpenCompass MMPreTrain

I obtained Ph.D. in Computer Science at the University of Chinese Academy of Science(UCAS), in the joint program at PLUS Lab, ShanghaiTech University in 2022. I got my B.Sc. degree in 2017 from Beihang University.

Open positions include full-time researchers/engineers and interns, feel free to contact me through the email. Research directions include: evaluation and application of large language model(tool use, reasoning, safety, robustness etc), multi-modality learning( vision/audio/-language learning), etc.

News

Nov 10, 2023 One paper on “Scene Graph Generation” is accepted by T-PAMI, Congratulations to Rongjie, welcome to SGTR+ for more details.
Oct 30, 2023 One paper on “Evaluating LLMs’ Multi-round Chatting Capability” is on arxiv, welcome to BotChat for more details.
Sep 30, 2023 One paper on “Benchmarking Legal Knowledge of Large Language Models” is on arxiv, welcome to LawBench for more details.
Jul 13, 2023 One paper on “Self-supervised Learning” is accepted by ICCV 2023, Congratulations to Yuan Liu.
Jul 12, 2023 One paper on “Benchmark for Multi-modality Learning” is posted on arxiv, welcome to MMBench for more details.
Feb 28, 2023 One paper on “Vision Backbone” is accepted by CVPR 2023, Congratulations to Jiahao Wang.
Feb 9, 2023 We organize the tutorial “OpenMMLab: A Foundational Platform for Computer Vision Research and Production” on AAAI 2023 Lab Forum.
Dec 5, 2022 I have been selected to Shanghai Post-doctoral Excellence Program .
Nov 5, 2022 Recieved the Champion of large-scale fine-grained classification [Code1][Code2][Certificate].
Jul 8, 2022 Two papers are accepted by ECCV 2022.

Selected Publications(Full List)

  1. ArXiv
    Fake Alignment: Are LLMs Really Aligned Well?
    Yixu Wang, Yan Teng, Kexin Huang, Chengqi Lyu, Songyang Zhang, and 3 more authors
    arXiv preprint arXiv:2311.05915 2023
  2. T-PAMI
    SGTR+: End-to-end Scene Graph Generation with Transformer
    Rongjie Li, Songyang Zhang, and Xuming He
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021, 2023
  3. ArXiv
    BotChat: Evaluating LLMs’ Capabilities of Having Multi-Turn Dialogues
    Haodong Duan, Jueqi Wei, Chonghua Wang, Hongwei Liu, Yixiao Fang, and 3 more authors
    2023
  4. ArXiv
    MMBench: Is Your Multi-modal Model an All-around Player?
    Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, and 7 more authors
    In arXiv Preprint, 2023
  5. IJCAI
    TG-VQA: Ternary Game of Video Question Answering
    Hao Li, Peng Jin, Zesen Cheng, Songyang Zhang, Kai Chen, and 3 more authors
    In Proceeding of International Joint Conferences on Artificial Intelligence (IJCAI), 2023
  6. ICCV
    Improving Pixel-based MIM by Reducing Wasted Modeling Capability
    Yuan Liu, Songyang Zhang, Jiacheng Chen, Zhaohui Yu, Kai Chen, and 1 more author
    In Proceedings of the IEEE/CVF International Conference on Computer Vision(ICCV), 2023
  7. CVPR
    RIFormer: Keep Your Vision Backbone Effective But Removing Token Mixer
    Jiahao Wang, Songyang Zhang, Yong Liu, Taiqiang Wu, Yujiu Yang, and 4 more authors
    In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  8. CVPR
    SGTR: End-to-end Scene Graph Generation with Transformer
    Rongjie Li, Songyang Zhang, and Xuming He
    In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  9. NeurIPS
    Dynamic Grained Encoder for Vision Transformers
    Lin Song*, Songyang Zhang*, Songtao Liu, Zeming Li, Xuming He, and 3 more authors
    In Proceeding of Advances in Neural Information Processing Systems (NeurIPS), 2021
  10. CVPR
    Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
    Songyang Zhang, Zeming Li, Shipeng Yan, Xuming He, and Jian Sun
    In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
  11. ICML
    LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
    Songyang Zhang, Shipeng Yan, and Xuming He
    In Proceeding of the 36th International Conference on Machine Learning (ICML),, 2019