Jiacai Liu - RankMe

18 papers A* 1C 1Journal 16

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It. CoRR Yaxiang Zhang, Yingru Li, Jiacai Liu, Jiawei Xu, Ziniu Li, Qian Liu, Haoyuan Li
2026	J	`jnl`	The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL. CoRR Yingru Li, Jiawei Xu, Ziniu Li, Jiacai Liu, Wei Liu, Yuxuan Tong, Longtao Zheng, Zhenghai Xue, Yaxiang Zhang, Tianle Cai, Ge Zhang, Qian Liu, Baoxiang Wang
2025	J	`jnl`	A Note on Hybrid Online Reinforcement and Imitation Learning for LLMs: Formulations and Algorithms. CoRR Yingru Li, Ziniu Li, Jiacai Liu
2025	J	`jnl`	Equal Division Contribution Values of Trapezoidal Fuzzy Numbers and Their Application to Profit Allocation in Cold Chain Logistics for Agricultural Products. Symmetry Jungan Zhan, Rong Fan, Minghao Liu, Jiacai Liu, Wenjian Zhao
2025	J	`jnl`	Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents. CoRR Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, Ke Wang
2025	J	`jnl`	On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation. CoRR Jiacai Liu, Wenye Li, Ke Wei
2025	J	`jnl`	On the Convergence of Projected Policy Gradient for Any Constant Step Sizes. J. Mach. Learn. Res. Jiacai Liu, Wenye Li, Dachao Lin, Ke Wei, Zhihua Zhang
2025	J	`jnl`	Policy Mirror Descent with Temporal Difference Learning: Sample Complexity under Online Markov Data. CoRR Wenye Li, Hongxu Chen, Jiacai Liu, Ke Wei
2025	J	`jnl`	Skywork Open Reasoner 1 Technical Report. CoRR Jujie He, Jiacai Liu, Chris Yuhao Liu, Rui Yan, Chaojie Wang, Peng Cheng, Xiaoyu Zhang, Fuxiang Zhang, Jiacheng Xu, Wei Shen, Siyuan Li, Liang Zeng, Tianwen Wei, Cheng Cheng, Bo An, Yang Liu, Yahui Zhou
2025	J	`jnl`	Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy. CoRR Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao, Jujie He, Jiacai Liu, Chaojie Wang, Rui Yan, Wei Shen, Fuxiang Zhang, Jiacheng Xu, Yang Liu, Yahui Zhou
2025	J	`jnl`	Taming the Tail: Stable LLM Reinforcement Learning via Dynamic Vocabulary Pruning. CoRR Yingru Li, Jiawei Xu, Jiacai Liu, Yuxuan Tong, Ziniu Li, Tianle Cai, Ge Zhang, Qian Liu, Baoxiang Wang
2025	J	`jnl`	Trust Region Masking for Long-Horizon LLM Reinforcement Learning. CoRR Yingru Li, Jiacai Liu, Jiawei Xu, Yuxuan Tong, Ziniu Li, Baoxiang Wang
2025	A*	`conf`	ϕ-Update: A Class of Policy Update Methods with Policy Convergence Guarantee. ICLR Wenye Li, Jiacai Liu, Ke Wei
2024	J	`jnl`	Elementary Analysis of Policy Gradient Methods. CoRR Jiacai Liu, Wenye Li, Ke Wei
2024	J	`jnl`	Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization. CoRR Jiacai Liu, Chaojie Wang, Chris Yuhao Liu, Liang Zeng, Rui Yan, Yiwen Sun, Yang Liu, Yahui Zhou
2024	J	`jnl`	Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs. CoRR Chris Yuhao Liu, Liang Zeng, Jiacai Liu, Rui Yan, Jujie He, Chaojie Wang, Shuicheng Yan, Yang Liu, Yahui Zhou
2023	J	`jnl`	On the Linear Convergence of Policy Gradient under Hadamard Parameterization. CoRR Jiacai Liu, Jinchi Chen, Ke Wei
2013	C	`conf`	Detection of hydrothermally alteration rocks in the east Gandise, Tibet (China) using aster imagery. IGARSS Zhaoqiang Huang, Jiacai Liu, Xuefeng Sun