SW
Shaohang Wei
cs.LGcs.AIcs.CLcs.CV
On Valency
published · living versionsW_w4wr4u5m·v1 · currentpublished
CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents
with Wenhao Yu, Zhengcheng Wang, Jiahong Liu, Zexuan Qiu +5
1 version
Preprints & journals
9 papers in the corpus · 2025–2026CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents2610.29965v1 · Wenhao Yu, Zhengcheng Wang, Jiahong Liu et al.2026 · 0 citationsarXivon Valency
On-Policy Visual Evidence Distillation2609.36838v1 · Shaohang Wei, Feifan Song, Guangyue Peng et al.2026 · 0 citationsarXiv
Verifier-Induced Support Reshaping in On-Policy Optimization2608.00220v2 · Shaohang Wei, Zikun Su, Feifan Song et al.2026 · 0 citationsarXiv
Experience Augmented Policy Optimization for LLM Reasoning2606.30420v2 · Jinda Lu, Kexin Huang, Junkang Wu et al.2026 · 0 citationsarXiv
One-Way Policy Optimization for Self-Evolving LLMs2605.22156v1 · Shuo Yang, Jinda Lu, Kexin Huang et al.2026 · 0 citationsarXiv
Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality2605.01749v1 · Wen Luo, Guangyue Peng, Liang Wang et al.2026 · 0 citationsarXiv
Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs2603.22446v1 · Haoming Meng, Kexin Huang, Shaohang Wei et al.2026 · 0 citationsarXiv
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning2602.01745v2 · Wenhao Yu, Shaohang Wei, Jiahong Liu et al.2026 · 1 citationarXiv
Mitigating Overthinking through Reasoning Shaping2510.09535v1 · Feifan Song, Shaohang Wei, Bofei Gao et al.2025 · 0 citationsarXiv
Career total: 10 works. 9 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.