Author

Jiashun Liu

Observed name: Liu, Jiashun

Institutions: Hong Kong University of Science and Technology, Fudan University, Alibaba Group (China)

Observed institutions: Hong Kong University of Science and Technology, Fudan University, Alibaba Group (China)

OpenAlex ID: A5132872093

Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms

2026 · Wu, Siye, Yang, Kai, et al. · arXiv (Cornell University)

Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions

2026 · Liu, Bingxu, Liu, Jiashun, et al. · arXiv (Cornell University)

The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning

2026 · Wu, Zihao, Tang, Hongyao, et al. · arXiv (Cornell University)

PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs

2026 · Yuanqiang Yu, Yanzhao Zheng, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Works count: 4

Citation count:

H-index:

I10-index: