陈冠旭

上海交通大学博士生，与上海人工智能实验室联合培养，导师为邵婧博士。

Google Scholar / 简历 / English

论文与技术报告

大推理模型与强化学习

1. Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
   Guanxu Chen, Yafu Li, Yuxian Jiang, Chen Qian, Qihan Ren, Jingyi Yang, Yu Cheng, Dongrui Liu, Jing Shao.
   ICLR 2026.

2. Rethinking Entropy Regularization in Large Reasoning Models
   Yuxian Jiang, Yafu Li, Guanxu Chen, Dongrui Liu, Yu Cheng, Jing Shao.
   arXiv preprint.

可信 AI

1. Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
   Guanxu Chen, Dongrui Liu, Tao Luo, Lijie Hu, Jing Shao.
   ICML 2026.

2. SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
   技术报告。
   核心贡献者之一。

3. Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
   技术报告。
   核心贡献者之一。

循环 Transformer 与潜在推理

1. Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?
   Guanxu Chen, Dongrui Liu, Jing Shao.
   技术报告。

Masked Diffusion Language Models

1. Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Steps
   Jingyi Yang, Guanxu Chen, Xuhao Hu, Jing Shao.
   arXiv preprint.