Lifan Yuan

How Far Can Unsupervised RLVR Scale LLM Training?

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones

Process Reinforcement through Implicit Rewards

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models

TTRL: Test-Time Reinforcement Learning

Advancing LLM Reasoning Generalists with Preference Trees

Free Process Rewards without Process Labels

Improving Zero-Shot Generalization of Instruction Tuning by Data Arrangement