activity
20242026
collaborators

5 papers

cs.CL2026

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

Yu Wang, Yi-Kai Zhang, Wentao Shi +8

Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR)…

cs.CV2026

The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

Xiang Chen, Hao Li, Jiangxin Dong +89

This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-wo…

cs.LG2025

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking

Yuchun Miao, Liang Ding, Sen Zhang +3

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major c…

cs.CV2025

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders

Yuqi Zhang, Yuchun Miao, Zuchao Li +1

We introduce AMIA, a lightweight, inference-only defense for Large Vision-Language Models (LVLMs) that (1) Automatically Masks a small set of text-irrelevant image patches to disru…

cs.LG2025

The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking

Yuchun Miao, Sen Zhang, Liang Ding +3

This work identifies the Energy Loss Phenomenon in Reinforcement Learning from Human Feedback (RLHF) and its connection to reward hacking. Specifically, energy loss in the final la…