by Zecheng Wang Papers
3 papers found
Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization
Deyuan Liu, Zecheng Wang, Bingning Wang et al.
ICML 2025poster
VPO: Reasoning Preferences Optimization Based on $\mathcal{V}$-Usable Information
Zecheng Wang, Chunshan Li, Yupeng Zhang et al.
NeurIPS 2025spotlight
Pre-training with Synthetic Data Helps Offline Reinforcement Learning
Zecheng Wang, Che Wang, Zixuan Dong et al.
ICLR 2024poster