Chao Yang

杨超, Research Scientist, Shanghai AI Lab.

yangchao.png

I am Research Scientist at Shanghai AI Lab (上海人工智能实验室), leading a Fundamental Large Model Safety & Decision Intelligence research group.

Recently, I have completed my postdoctoral fellowship under the guidance of Professor Yu Qiao , where my research focused on the security aspects of large-scale models. My work delved into the vulnerabilities and defense mechanisms associated with AI systems, particularly in the context of large language models and their applications.

Previously, I received my Ph.D. in Department of Computer Science and Technology at Tsinghua University in 2022, advised by Prof. Fuchun Sun and Prof. Huaping Liu.

My research interest includes Large Language Model Safety, Multi-modal Large Model, and Robotic Embodied Intelligence for Trustworthy AGI. Some of my current research keywords can be found below:

  • Large Language Model: LLM Post-training and Safety Alignment, LLM Attack and Defense.
  • Multimodal LLM: Modality Fusion, Multimodal alignment, VQA.
  • Embodied Robotics: Robotic Manipulation, Reinforcement Learning, Imitation Learning.

For Academic Cooperation, please feel free to email me at yangchao[at] pjlab [dot] org [dot] cn. For other matters, please contact me at yangchao9264 [at] 126 [dot] com or yangchaoemigmo [at] gmail [dot] com.

news

Jul 15, 2025 🎉 Big Project Release! We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. SafeWork-R1 :rocket: :sparkles:
Jun 04, 2025 We find patches from harmful content, enabling them to bypass data moderation and generate dangerous responses when encountering the full image or related text. VLMs Can Aggregate Scattered Training Patchesk :sparkles:
May 16, 2025 Our paper Adversarial Preference Learning for Robust LLM Alignment is accepted by ACL2025. Arxiv Link :sparkles:
May 02, 2025 [ICML2025] Emergent Response Planning in LLM and C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation are accepted by ICML2025. :sparkles:
Dec 08, 2024 We proposal a new law, AI 45°-Law toward trustworthy AGI! Arxiv Link :sparkles:
Sep 26, 2024 Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models is accepted by NeurIPS 2024. NeurIPS Link :sparkles::sparkles:
Sep 23, 2024 Inference-Time Language Model Alignment via Integrated Value Guidance is accepted by EMNLP 2024. Arixv Link :sparkles::sparkles:
Jul 04, 2024 MM-SafetyBench (A Benchmark for Safety Evaluation of Multimodal Large Language Models) is accepted by ECCV 2024. Project Page. :sparkles::sparkles:
May 16, 2024 Three Papers (Emulated Disalignment, Structured Reasoning, Multi-Objective DPO) are accepted by ACL 2024.:sparkles::sparkles:

selected publications

  1. CVPR2024
    VideoDistill: Language-aware Vision Distillation for Video Question Answering
    Bo Zou*, Chao Yang*, Yu Qiao, and 2 more authors
    arXiv preprint arXiv:2404.00973, 2024
    PDF
  2. CVPR2024
    LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction
    Bo Zou*, Chao Yang*, Yu Qiao, and 2 more authors
    2024
    PDF
  3. ACL2024 Oral
    Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
    Zhanhui Zhou, Jie Liu, Zhichen Dong, and 4 more authors
    arXiv preprint arXiv:2402.12343, 2024
  4. NAACL2024
    Attacks, defenses and evaluations for llm conversation safety: A survey
    Zhichen Dong, Zhanhui Zhou, Chao Yang+, and 2 more authors
    arXiv preprint arXiv:2402.09283, 2024
  5. AAAI2024
    Critic-guided decision transformer for offline reinforcement learning
    Yuanfu Wang, Chao Yang, Ying Wen, and 2 more authors
    arXiv preprint arXiv:2312.13716, 2023
  6. ECCV2024
    Safety of Multimodal Large Language Models on Images and Text
    Xin Liu, Yichen Zhu, Yunshi Lan, and 2 more authors
    arXiv preprint arXiv:2402.00357, 2024