post-alignment

AI & ML interests

None defined yet.

Recent Activity

nlile  authored a paper 5 days ago

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning

nlile  authored a paper 4 months ago

Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

nlile  authored a paper 4 months ago

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

View all activity

Team members 2