Reinforcement Learning and Large Language Models is the fifth lecture of ScienceOne.

Details of the Lecture

In this session, Prof. ZHANG Qichao will introduce the concepts of reinforcement learning and large language model (LLM) reasoning. It first presents the basic preliminaries of reinforcement learning, then demonstrates common techniques for LLM reasoning. The talk also covers the ScienceOne post-training methodology and its application to astronomy tasks.

Speaker Profile

ZHANG Qichao is a professor at the Institute of Automation, Chinese Academy of Sciences. His research focuses on reinforcement learning and large language model reasoning. He is a recipient of the Dean's Award of the Chinese Academy of Sciences. He has published over 80 papers in CCF-A/B conferences and IEEE Transactions journals, with over 3,800 citations. As a core member, he developed reinforcement learning post-training algorithms for the ScienceOne Foundation Model. He has also established collaborations with multiple companies, including Meituan and Baidu, among others.

Date & Time

15:00–16:00 (Beijing Time, GMT+8)

June 16, 2026

Organizers

● Alliance of National and International Science Organizations for the Belt and Road Regions (ANSO)

● Institute of Automation, Chinese Academy of Sciences (CASIA)

Online Access (Microsoft Teams)

Meeting Link: https://teams.live.com/meet/9356063392996?p=qL5Qvqq5TyF7pHo5zd

Meeting ID: 935 606 339 299 6

Passcode: fV3we7