Image de couverture de livre

DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yangfu, Zhan, Hongjian, Chen, Jiawei, Gong, Yuning, Liu, Qi, Lu, Yue
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Perceptual Flow Network for Visually Grounded Reasoning
par: Li, Yangfu, et autres
Publié: (2026)

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
par: Li, Yangfu, et autres
Publié: (2025)

GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
par: Zhou, Yue, et autres
Publié: (2024)

See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs
par: Zhang, Yongchang, et autres
Publié: (2026)

Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning
par: Luo, Liqin, et autres
Publié: (2025)

DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models
par: Wang, JiYang, et autres
Publié: (2026)

EGM: Efficient Visual Grounding Language Models
par: Zhan, Guanqi, et autres
Publié: (2026)

KPL: Training-Free Medical Knowledge Mining of Vision-Language Models
par: Liu, Jiaxiang, et autres
Publié: (2025)

View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs
par: Liu, Yuanyuan, et autres
Publié: (2025)

ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
par: Lv, Guannan, et autres
Publié: (2026)

Language-to-Space Programming for Training-Free 3D Visual Grounding
par: Mi, Boyu, et autres
Publié: (2025)

MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?
par: Wang, Yuandong, et autres
Publié: (2025)

Personalization Toolkit: Training Free Personalization of Large Vision Language Models
par: Seifi, Soroush, et autres
Publié: (2025)

AgriChain Visually Grounded Expert Verified Reasoning for Interpretable Agricultural Vision Language Models
par: Mahmood, Hazza, et autres
Publié: (2026)

Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
par: Gröpl, Marcel, et autres
Publié: (2026)

Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
par: Xiang, Ziwei, et autres
Publié: (2026)

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
par: Yoon, Hee Suk, et autres
Publié: (2026)

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
par: Huang, Hsiang-Wei, et autres
Publié: (2026)

Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models
par: Yang, Xiaoyu, et autres
Publié: (2023)

Reasoning or Pattern Matching? Probing Large Vision-Language Models with Visual Puzzles
par: Lymperaiou, Maria, et autres
Publié: (2026)

SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models
par: Cheng, An-Chieh, et autres
Publié: (2024)

Learning Visual Grounding from Generative Vision and Language Model
par: Wang, Shijie, et autres
Publié: (2024)

Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark
par: Yuan, Haobo, et autres
Publié: (2025)

CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models
par: Anand, Neeraj, et autres
Publié: (2026)

Large Language Models are Universal Reasoners for Visual Generation
par: Ren, Sucheng, et autres
Publié: (2026)

VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscripts
par: Hu, Wenbo, et autres
Publié: (2023)

EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
par: Lu, Hongyu, et autres
Publié: (2026)

ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities
par: Zhu, Chenming, et autres
Publié: (2024)

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
par: Lee, Daeun, et autres
Publié: (2026)

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models
par: Wu, Mingrui, et autres
Publié: (2024)

UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing
par: Zhang, Jiaxi, et autres
Publié: (2026)

VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models
par: Ren, Yufan, et autres
Publié: (2025)

Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
par: Liu, Zuyan, et autres
Publié: (2024)

RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
par: Xu, Jingqi, et autres
Publié: (2025)

Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
par: Lee, Seulbi, et autres
Publié: (2026)

Grounded 3D-Aware Spatial Vision-Language Modeling
par: Cheng, An-Chieh, et autres
Publié: (2026)

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
par: Xue, Haotian, et autres
Publié: (2025)

Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos
par: Pan, Yulin, et autres
Publié: (2023)

Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation
par: Chen, Bolei, et autres
Publié: (2025)

One CT Unified Model Training Framework to Rule All Scanning Protocols
par: Xu, Fengzhi, et autres
Publié: (2026)