AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs

Yanbin Wei, Jiangyue Yan, Chun Kang, Yang Chen, Hua Liu, James Kwok, Yu Zhang

CVPR 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
route each question to its preferred GTR instead of one fixed GTR (ablation)VLM graph QA (GPT-4o) · In-domain graph QAAvg. GRE: 1.21 -> 1.67Improved
add DynamicGTR router to GPT-4o on cycle detectionGPT-4o · Cycle detectionaccuracy: 68.7 -> 89.3Improved
add DynamicGTR router on topological sortGPT-4o · Topological sortaccuracy: 40.9 -> 40.8No clear effect
add DynamicGTR router for token savings on topological sortGPT-4o · Topological sorttoken consumption: 256.1 -> 176.1Improved
apply router trained on synthetic algorithm QA to unseen real-world node classificationGPT-4o · PolBlogaccuracy: 63.6 -> 71.9Improved
use Tmat (adjacency matrix) as the only GTR (ablation)GPT-4o · In-domain graph QAAvg. GRE: 1.05 -> 0.56Hurt
lower alpha from 0.5 to 0 (accuracy only) (ablation)DynamicGTR · In-domain graph QAtoken consumption: 212.0 -> 290.8Mixed
raise alpha from 0.5 to 1 (ablation)DynamicGTR · In-domain graph QAaccuracy: 69.5 -> 69.3Mixed
increase probing trials k from 1 to 10 (ablation)GTR preference dataset · In-domain graph QAaccuracy: 62.4 -> 69.5Improved
increase probing trials k from 1 to 10 (ablation)GTR preference dataset · In-domain graph QAtoken consumption: 286.2 -> 212.0Improved
use Gemini-2.5 Pro's router on GPT-4o instead of native router (ablation)GTR router · Cross-model transfer, averageaccuracy: -0.6No clear effect
use GPT-4o's router on Gemini-2.5 Pro instead of native router (ablation)GTR router · Cross-model transfer, averageaccuracy: +0.2No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy