← Search

Zhao Junsuo

2 accepted papers

2026

Efficient Code Analysis via Graph-Guided Large Language Models

ICML 2026poster

Large Language Models (LLMs) have significantly advanced code analysis tasks, yet they struggle to detect malicious behaviors fragmented across files, whose intricate dependencies easily get lost in the vast amount of benign code. We therefore propose a graph-centric attention acquisition pipeline t…

Cited by 0SourceScholar
2025

LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification

ICML 2025poster

The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the fundamental properties of this approach remain underexplored.…

Cited by 0SourcePDFScholar