6 papers
Understanding Diversity Collapse in RLVR via the Lens of Overtraining
Suqin Yuan, Jinkun Chen, Jiyang Zheng +6
Reinforcement learning with verifiable rewards (RLVR) has become a key approach for enhancing the reasoning abilities of large language models. However, RLVR often suffers from \em…
Mitigating Mismatch within Reference-based Preference Optimization
Suqin Yuan, Xingrui Yu, Jiyang Zheng +4
Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models, but its reliance on a reference policy introduces a…
Unifying Stable Optimization and Reference Regularization in RLHF
Li He, Qiang Qu, He Zhao +4
Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: \textbf{reward hacking} and \textbf…
DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection
Jialiang Shen, Jiyang Zheng, Yunqi Xue +8
With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle u…
Direct Advantage Regression: Aligning LLMs with Online AI Reward
Li He, He Zhao, Stephen Wan +3
Online AI Feedback (OAIF) presents a promising alternative to Reinforcement Learning from Human Feedback (RLHF) by utilizing online AI preference in aligning language models (LLMs)…
Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising
Yongli Xiang, Ziming Hong, Lina Yao +2
Non-transferable learning (NTL) has been proposed to protect model intellectual property (IP) by creating a "non-transferable barrier" to restrict generalization from authorized to…