4 papers
COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents
Wenkai Shen, Pengyang Zhou, Jiahe Xu +5
LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmful intents may decompose int…
Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling
Weijie Zhao, Mingquan Liu, Bolun Wang +4
Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identif…
ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction
Wenda Liu, Zhigang Song, Shuai Nie +11
LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases training complexity yet often yield…
FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models
Xinting Liao, Weiming Liu, Jiaming Qian +6
Federated prompt learning (FPL) for vision-language models is a powerful approach to collaboratively adapt models across distributed clients while preserving data privacy. However,…