Jiacai Liu
Scholar

Jiacai Liu

Google Scholar ID: zt9Jfh4AAAAJ
Fudan University
reinforcement learning
Google Scholar↗
Citations & Impact
All-time
Citations
325
 
H-index
6
 
i10-index
5
 
Publications
12
 
Co-authors
5
list available
Contact
No contact links provided.
Publications
10 items
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
2026
Cited
0
Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It
2026
Cited
1
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
2025
Cited
0
A Note on Hybrid Online Reinforcement and Imitation Learning for LLMs: Formulations and Algorithms
2025
Cited
0
Taming the Tail: Stable LLM Reinforcement Learning via Dynamic Vocabulary Pruning
2025
Cited
0
On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation
2025
Cited
0
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
2025
Cited
0
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
2025
Cited
0
Resume (English only)
Co-authors
5 total
Chaojie Wang
Chaojie Wang
AI Researcher, Skywork AI
Liang Zeng
Liang Zeng
Skywork AI; IIIS, Tsinghua University
Chris Yuhao Liu
Chris Yuhao Liu
University of California, Santa Cruz
Jiawei Wang
Jiawei Wang
University of Science and Technology of China
Yuqian Fu
Yuqian Fu
Institute of Automation，Chinese Academy of Sciences