Songyang Zhang
Young Researcher at Shanghai AI Laboratory, Shanghai, China.
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.
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
Mar 26, 2024 | Technical report of InternLM2 has been released, welcome to InternLM2 for more details. |
---|---|
Mar 14, 2024 | Three papers accepted by NAACL 2024, Fake Alignment, BotChat and AdaEval. |
Feb 29, 2024 | One paper on “SGG with Vision-langauge Model” is accepted by CVPR 2024, congratulations to Rongjie. |
Nov 10, 2023 | One paper on “T-Eval” is on Arxiv, welcome to T-Eval for more details. |
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. |
Selected Publications(Full List)
- CVPRFrom Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language ModelsIn Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
- NAACLFake Alignment: Are LLMs Really Aligned Well?In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024
- T-PAMISGTR+: End-to-end Scene Graph Generation with TransformerIn IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
Awards
Webly-supervised Fine-grained Image Classification, Champion, ACCV 2022. [Code-P1][Code-P2][Certificate] |
System Design Contest(SDC) ,Champion, DAC 2021 |
LVIS Challenge, 2nd Place, ICCV 2021 |
Workshop on Autonomous Driving(WAD) streaming detection challenge,Champion, CVPR 2021 |