5 papers
Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
Xueqi Ma, Shuo Yang, Yanbei Jiang +6
Despite remarkable advances in large Vision-Language Models (VLMs), spatial reasoning remains a persistent challenge. In this work, we investigate how attention heads within VLMs c…
EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection
Shuo Yang, Soyeon Caren Han, Xueqi Ma +3
LLM-based agents depend on effective tool-use policies to solve complex tasks, yet optimizing these policies remains challenging due to delayed supervision and the difficulty of cr…
Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
Xueqi Ma, Xingjun Ma, Sarah Monazam Erfani +2
Developing open-set classification methods capable of classifying in-distribution (ID) data while detecting out-of-distribution (OOD) samples is essential for deploying graph neura…
Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules
Yanbei Jiang, Xueqi Ma, Shu Liu +5
Despite excelling on multimodal benchmarks, vision-language models (VLMs) largely remain a black box. In this paper, we propose a novel interpretability framework to systematically…
Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
Xueqi Ma, Jun Wang, Yanbei Jiang +3
Large language models (LLMs) have achieved state-of-the-art performance in a variety of tasks, but remain largely opaque in terms of their internal mechanisms. Understanding these…