tracked author

Jian Hu

ProRL/BroRL recurring author; NVIDIA author page and personal blog align with OpenRLHF/REINFORCE++ and RLHF/RLVR systems work, but no high-confidence personal X account was found.

2 archived notes X: not-found Homepage

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

归档 Apr 08, 2026

BroRL: Scaling Reinforcement Learning via Broadened Exploration

把 RLVR scaling 轴扩展到 rollout width，并用 correct mass decomposition 解释宽采样收益。

待审阅 2510.01180-brorl-broadened-rl-exploration Rollout Optimization Reasoning RL RL Algorithm

归档 Mar 10, 2026

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

用高温探索、动态采样、周期 reference / optimizer reset 延长 RL，测试 reasoning boundary 扩展。

待审阅 2505.24864-prorl-prolonged-rl-reasoning-boundaries Reasoning RL RL Algorithm Rollout Optimization