Get started
Author

Weixun Wang

Observed name: Wang, Weixun
Observed institution: Alibaba Group (China)
OpenAlex ID: A5124005698
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
2026 · Liang, Jing, Tang, Hongyao, et al. · arXiv (Cornell University)
PDF
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
2026 · Dong, Zhichen, Li, Yang, et al. · arXiv (Cornell University)
PDF
Think-J: Learning to Think for Generative LLM-as-a-Judge
2026 · Hui Huang, Yancheng He, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria
2026 · Hu, Xinyu, He, Yancheng, et al. · arXiv (Cornell University)
PDF
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants
2026 · Wang, Pei, Wu, Yanan, et al. · arXiv (Cornell University)
PDF
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants
2026 · Pei Wang, Yanan Wu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria
2026 · Xinyu Hu, Yancheng He, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Works count: 7
Citation count:
H-index:
I10-index:
Year
Topic
Type