Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning

arXiv:2608.04452 · cs.CV, cs.AI, cs.CL · Submitted 2026-08-05 · Read on arXiv

cs.CV, cs.AI, cs.CL

Submitted: 2026-08-05

Updated: 2026-09-24

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Composition — 25× in this paper · explained in 2 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Localization — 22× in this paper · explained in 2 episodes
• Accuracy — 19× in this paper · explained in 1 episode
• Ablation — 5× in this paper · explained in 1 episode
• Calibration — 5× in this paper · explained in 9 episodes
• Core — 3× in this paper · explained in 2 episodes
• Frozen model — 3× in this paper · explained in 3 episodes
• Trace — 3× in this paper · explained in 2 episodes
• MLLMs — 2× in this paper · explained in 2 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Failure Taxonomy — 1× in this paper · explained in 4 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception
• PaddleOCR 3.0 Technical Report
• PP-OCR: A Practical Ultra Lightweight OCR System
• Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
• LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models
• PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models