Article
Recreating o1 at Home with Role-Play LLMs
wenbopan
• • 23
Wenbo Pan
wenbopan
AI & ML interests
Make interesting and accessible models & datasets.
Recent Activity
authored a paper 28 days ago
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts authored a paper about 1 month ago
The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions updated a dataset about 1 month ago
wenbopan/safety-residual-spaceOrganizations
published an article almost 2 years ago
published an article about 2 years ago
Article
Everything About Long Context Fine-tuning
wenbopan
• • 57