collaborators

5 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.LG2025

Towards Better Generalization via Distributional Input Projection Network

Yifan Hao, Yanxin Lu, Hanning Zhang +2

As overparameterized models become increasingly prevalent, training loss alone offers limited insight into generalization performance. While smoothness has been linked to improved…

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

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

Jiarui Yao, Yifan Hao, Hanning Zhang +4

Chain-of-thought (CoT) reasoning in large language models (LLMs) can be formalized as a latent variable problem, where the model needs to generate intermediate reasoning steps. Whi…