collaborators

6 papers

cs.LG2026

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL

Chenlu Ye, Xuanchang Zhang, Yifan Hao +6

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribut…

cs.LG2026

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training

Chenlu Ye, Zhou Yu, Ziji Zhang +5

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards…

cs.LG2026

Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less

Yuxing Liu, Jianyu Wang, Tong Zhang

Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetunin…

cs.LG2025

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models

Yifan Hao, Chenlu Ye, Chi Han +1

Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output exa…

cs.AI2025

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods

Yifan Hao, Xingyuan Pan, Hanning Zhang +3

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models ten…

cs.LG2025

Daunce: Data Attribution through Uncertainty Estimation

Xingyuan Pan, Chenlu Ye, Joseph Melkonian +2

Training data attribution (TDA) methods aim to identify which training examples influence a model's predictions on specific test data most. By quantifying these influences, TDA sup…