Bingxiang He

Towards a Unified View of Large Language Model Post-Training

How Far Can Unsupervised RLVR Scale LLM Training?

CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial Observations

CPMöbius: Iterative Coach–Player Reasoning for Data-Free Reinforcement Learning

Process Reinforcement through Implicit Rewards

AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset

Improving Zero-Shot Generalization of Instruction Tuning by Data Arrangement