Tag
This paper analyzes how large language models internally process graph tokens in Graph Language Models (GLMs), finding a decoupling between activation-level saliency and graph-semantic utility. Graph sink tokens emerge as activation outliers but are not the primary carriers of graph structure, revealing limitations in current graph-token construction and alignment mechanisms.
This paper presents a graph-learning-aided optimization approach for designing active tether-net systems to capture space debris, using a GNN to recommend candidate designs and reduce mixed-combinatorial nonlinear programming to standard NLP problems, achieving faster convergence.
This paper introduces GraphReAct, a framework that extends reasoning-acting paradigms to graph-structured data for multi-step inference. It combines topological and semantic retrieval with context refinement to improve performance on graph learning benchmarks.