1 citations · 1 across the 13 of their papers we have counts for
4 papers · 1 filter
On the Geometry of On-Policy Distillation
Zhennan Shen, Yanshu Li, Qingyu Yin +6
On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of O…
Evaluating Parameter Efficient Methods for RLVR
Qingyu Yin, Yulun Wu, Zhennan Shen +6
We systematically evaluate Parameter-Efficient Fine-Tuning (PEFT) methods under the paradigm of Reinforcement Learning with Verifiable Rewards (RLVR). RLVR incentivizes language mo…
Adversarial Training of Reward Models
Alexander Bukharin, Haifeng Qian, Shengyang Sun +6
Reward modeling has emerged as a promising approach for the scalable alignment of language models. However, contemporary reward models (RMs) often lack robustness, awarding high re…
Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment
Shengyang Sun, Yian Zhang, Alexander Bukharin +11
The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different…