Kai YeStatistics · LSE

Talks & teaching

Talks & presentations

For full talk details and slides, visit my talks homepage ↗.

  1. BASIS: Information Sharing for Single-Rollout LLM Reasoning

    Gouxionghui Online Seminar · Online

    Invited talk [Slides] [Recording]

  2. Large Language Models (LLMs): Principles and Training Methods

    4th Conference on Machine Learning and Statistics (MLSTAT 2026) · Southwestern University of Finance and Economics, Chengdu, China

    Invited talk [Slides] [Conference details]

  3. VRPO: Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning

    Gouxionghui Online Seminar · Online

    Invited talk [Slides] [Recording]

  4. VRPO: Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning

    Annual Conference of the Chinese Statistical Association of Young Scholars · China

    Invited talk [Slides]

Teaching