tracked author

Jiawei Xu

TRM equal contribution author and OTB co-first author. OpenReview profile identifies him as a CUHK-Shenzhen PhD student with LLM post-training and reinforcement learning expertise; CUHK-Shenzhen SDS student search lists him as a 2023 PhD student supervised by Baoxiang Wang; GitHub `jiawei415` authored the merged verl OTB PR.

2 archived notes X: not-found Homepage GitHub

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 Jun 22, 2026

The Optimal Token Baseline: Variance Reduction for Long Horizon LLM RL

推导 token level variance minimizing baseline，并用 logit gradient proxy 近似长轨迹 policy gradient 权重。

待审阅 2602.07078-optimal-token-baseline-long-horizon-llm-rl Credit Assignment RL Algorithm RL Theory

归档 Jun 21, 2026

Trust Region Masking for Long Horizon LLM Reinforcement Learning

用序列级 max token divergence 约束 rollout policy mismatch，控制长轨迹 surrogate error。

待审阅 2512.23075-trust-region-masking-long-horizon-llm-rl Training Stability RL Algorithm Rollout Optimization