4 papers
DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation
Yuchen Xia, Qianguo Sun, Chao Song +3
On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student errors can lead a trajectory…
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
Zeyuan Liu, Zhihe Yang, Jiawei Xu +5
Real-world datasets collected from sensors or human inputs are prone to noise and errors, posing significant challenges for applying offline reinforcement learning (RL). While exis…
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
Zhihe Yang, Xufang Luo, Zilong Wang +4
Reinforcement learning (RL) has become a cornerstone for enhancing the reasoning capabilities of large language models (LLMs), with recent innovations such as Group Relative Policy…
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
Zhihe Yang, Xufang Luo, Dongqi Han +2
Hallucination remains a major challenge for Large Vision-Language Models (LVLMs). Direct Preference Optimization (DPO) has gained increasing attention as a simple solution to hallu…