Hongxin Ding

Dynamic rubrics that evolve with the policy can significantly enhance reinforcement learning performance, even without external supervision.

The $\ell_2$ norm of hidden states serves as a powerful indicator of reasoning intensity in LLMs, enabling new techniques that boost reasoning performance without extra training.

LLMs can reason far better on clinical records when demonstrations are selected using a graph-guided approach that combines patient data with LLM-estimated information gain.