Research talks and short courses by Kai Ye.
- Large Language Models: Principles and Training Methods — Open talk slides · Abstract & contents
- Can Tabular Foundation Models Amortize Statistical Inference? (TabCon) — Open talk slides · Abstract & contents · Paper
- BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning — Open talk slides · Abstract & contents · Paper
- VRPO: Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning — Open talk slides · Abstract & contents · Paper