Cover Image

The Dual Mechanisms of Spatial Reasoning in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cui, Kelly, Prakash, Nikhil, Raina, Ayush, Bau, David, Torralba, Antonio, Shaham, Tamar Rott
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Vision-Language Binding in In-Context Image Generation
by: Ge, Chris, et al.
Published: (2026)

A Vision Check-up for Language Models
by: Sharma, Pratyusha, et al.
Published: (2024)

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
by: Prakash, Nikhil, et al.
Published: (2024)

SketchAgent: Language-Driven Sequential Sketch Generation
by: Vinker, Yael, et al.
Published: (2024)

BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain
by: Wasserman, Navve, et al.
Published: (2025)

Dataset Distillation for Pre-Trained Self-Supervised Vision Models
by: Cazenavette, George, et al.
Published: (2025)

From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain
by: Golbari, Yuval, et al.
Published: (2026)

Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
by: Li, Christy, et al.
Published: (2025)

SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models
by: Xie, Yuechen, et al.
Published: (2026)

A Multimodal Automated Interpretability Agent
by: Shaham, Tamar Rott, et al.
Published: (2024)

ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
by: Zhao, Yanpeng, et al.
Published: (2026)

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
by: Chen, Boyuan, et al.
Published: (2024)

RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection
by: Zisman, Haim, et al.
Published: (2026)

Can Vision-Language Models See Squares? Text-Recognition Mediates Spatial Reasoning Across Three Model Families
by: Levental, Yuval
Published: (2026)

Logit Disagreement: OoD Detection with Bayesian Neural Networks
by: Raina, Kevin
Published: (2025)

Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models
by: Rajabi, Navid, et al.
Published: (2023)

TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
by: Li, Chengzu, et al.
Published: (2024)

RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception
by: Waite, Joshua R., et al.
Published: (2025)

MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?
by: Wang, Yuandong, et al.
Published: (2025)

Enhancing VICReg: Random-Walk Pairing for Improved Generalization and Better Global Semantics Capturing
by: Simai, Idan, et al.
Published: (2025)

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
by: Liu, Benlin, et al.
Published: (2024)

Spatial Reasoning with Denoising Models
by: Wewer, Christopher, et al.
Published: (2025)

Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
by: Zhang, Ce, et al.
Published: (2024)

Unified Concept Editing in Diffusion Models
by: Gandikota, Rohit, et al.
Published: (2023)

EasyARC: Evaluating Vision Language Models on True Visual Reasoning
by: Unsal, Mert, et al.
Published: (2025)

Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
by: Ling, Huan, et al.
Published: (2023)

Behavioural Cloning in VizDoom
by: Spick, Ryan, et al.
Published: (2024)

GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
by: Li, Ling, et al.
Published: (2024)

ThermEval: A Structured Benchmark for Evaluation of Vision-Language Models on Thermal Imagery
by: Shrivastava, Ayush, et al.
Published: (2026)

Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning
by: Harmanani, Mohamed, et al.
Published: (2026)

Sum-of-Checks: Structured Reasoning for Surgical Safety with Large Vision-Language Models
by: You, Weiqiu, et al.
Published: (2026)

HoneyBee: Data Recipes for Vision-Language Reasoners
by: Bansal, Hritik, et al.
Published: (2025)

Characterizing Model Robustness via Natural Input Gradients
by: Rodríguez-Muñoz, Adrián, et al.
Published: (2024)

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
by: Jiang, Feng, et al.
Published: (2025)

FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models
by: Huang, Chenyu, et al.
Published: (2026)

Simple Vision-Language Math Reasoning via Rendered Text
by: Skripkin, Matvey, et al.
Published: (2025)

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models
by: Huang, Xin, et al.
Published: (2025)

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information
by: Chu, Xu, et al.
Published: (2025)

Learning Shared Representations from Unpaired Data
by: Yacobi, Amitai, et al.
Published: (2025)

Sherlock: Self-Correcting Reasoning in Vision-Language Models
by: Ding, Yi, et al.
Published: (2025)