Reflector: Internalizing Step-wise Reflection against Indirect Jailbreaks
Ma, J., Zhang, J., Li, X., Zou, B., Lu, C., & Yang, C. (2026). "REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak." ICML 2026.
CV
Education
- B.S. in Computer Science and Communication Engineering, Zhejiang University, 2017-2021
Work experience
- 2024 - Present: Researcher
- Shanghai AI Lab
- Research focus: Large Language Model Post-training, Reinforcement Learning, Multi-agent Systems, and Multimodal AI
- 2021 - 2024: Research Engineer
- Huawei Technologies Co., Ltd.
- Research focus: Intersection of Communication and Artificial Intelligence
Skills
- Large Language Models (Post-training, Fine-tuning)
- Reinforcement Learning
- Multi-agent Systems
- Multimodal AI (Vision-Language Models)
- Deep Learning
- Python, PyTorch
- Research Tools Development (MCP servers)
Publications
Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
Wang, Y., Liu, Z., Li, X., Lu, C., & Yang, C. (2026). "Native Reasoning Models: Training Language Models to Reason on Unverifiable Data." ICLR 2026 Poster.
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law
Shanghai AI Lab et al. (2025). "SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law." arXiv preprint arXiv:2507.18576.
Talks
Conference Proceeding talk 3 on Relevant Topic in Your Field
Conference proceedings talk at Testing Institute of America 2014 Annual Conference, Los Angeles, CA, USA
Talk 2 on Relevant Topic in Your Field
Talk at London School of Testing, London, UK
Tutorial 1 on Relevant Topic in Your Field
Tutorial at UC-Berkeley Institute for Testing Science, Berkeley, CA, USA
Talk 1 on Relevant Topic in Your Field
Talk at UC San Francisco, Department of Testing, San Francisco, CA, USA
Teaching
Service and leadership
- (To be updated)