
- Sponsor
- Siebel School Academic Office
- Views
- 3
- Originating Calendar
- Siebel School Graduate Calendar
Thesis Title: Reinforcement Learning Algorithm Design for Large Language Models: From Preference Alignment to Complex Reasoning
Tong Zhang, Co-Chair and Co-Director of Research
Nan Jiang, Co-Chair and Co-Director of Research
Han Zhao
Jason Weston, Facebook
If you wish to attend via zoom, please email Chair or student for Zoom password prior to exam.