3 papers
cs.CR2025
"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
Zhen Sun, Zongmin Zhang, Deqi Liang +8
As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-cr…
cs.LG2025
Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs
Mengqi Liao, Xiangyu Xi, Ruinian Chen +5
Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate…
cs.CV2025
XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmark
Shuai Liu, Youmeng Li, Jizeng Wei
Document Reading Order Recovery is a fundamental task in document image understanding, playing a pivotal role in enhancing Retrieval-Augmented Generation (RAG) and serving as a cri…