Cover Image

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Min, Cheolhong, Jung, Jaeyun, Lee, Daeun, Jeon, Hyeonseong, Su, Yu, Tremblay, Jonathan, Song, Chan Hee, Park, Jaesik
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Tree-Guided Diffusion Planner
by: Jeon, Hyeonseong, et al.
Published: (2025)

RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics
by: Song, Chan Hee, et al.
Published: (2024)

Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models
by: Jang, Jaeyun, et al.
Published: (2026)

Your feelings are reasonable: Emotional validation promotes persistence among preschoolers
by: Jeewon Jeon, et al.
Published: (2024)

Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
by: Kim, Hee-Sung, et al.
Published: (2026)

Learning to Continually Learn with the Bayesian Principle
by: Lee, Soochan, et al.
Published: (2024)

CF3: Compact and Fast 3D Feature Fields
by: Lee, Hyunjoon, et al.
Published: (2025)

Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding
by: An, Na Min, et al.
Published: (2025)

IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution
by: Park, Sejin, et al.
Published: (2025)

Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models
by: Park, Bumjin, et al.
Published: (2025)

Memorizing Documents with Guidance in Large Language Models
by: Park, Bumjin, et al.
Published: (2024)

Identifying the Source of Generation for Large Language Models
by: Park, Bumjin, et al.
Published: (2024)

Revealing Multi-View Hallucination in Large Vision-Language Models
by: Park, Wooje, et al.
Published: (2026)

Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
by: Kim, Hyunjin, et al.
Published: (2025)

Video Color Grading via Look-Up Table Generation
by: Shin, Seunghyun, et al.
Published: (2025)

SVRecon: Sparse Voxel Rasterization for Surface Reconstruction
by: Oh, Seunghun, et al.
Published: (2025)

Improving the Machine Learning Stock Trading System: An N‐Period Volatility Labeling and Instance Selection Technique
by: Young Hun Song, et al.
Published: (2024)

SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization
by: Park, Yeonsik, et al.
Published: (2026)

Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information
by: Joung, Youngju, et al.
Published: (2025)

Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
by: Park, Keon-Hee, et al.
Published: (2024)

VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments
by: Song, Daeun, et al.
Published: (2024)

SpatialMosaic: A Multiview VLM Dataset for Partial Visibility
by: Lee, Kanghee, et al.
Published: (2025)

Development of Marine‐Degradable Poly(Ester Amide)s with Strong, Up‐Scalable, and Up‐Cyclable Performance
by: Sung Bae Park, et al.
Published: (2024)

Analyzing Process Data from Computer-Based Assessments: A Tutorial on Preprocessing, Feature Extraction, and Model-Based Inference
by: Hwangbo, Daeun, et al.
Published: (2026)

AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning
by: Kong, Yangzhe, et al.
Published: (2025)

Unifying reciprocal and real space atomic dynamics in dilute gases
by: Moon, Jaeyun
Published: (2026)

Microscopic view of materials properties of liquids: An atomic scale perspective
by: Moon, Jaeyun
Published: (2026)

Psychological capital and individual performance via social capital
by: Jaeyun Jeong
Published: (2025)

Recovering Dynamic 3D Sketches from Videos
by: Lee, Jaeah, et al.
Published: (2025)

3Doodle: Compact Abstraction of Objects with 3D Strokes
by: Choi, Changwoon, et al.
Published: (2024)

Towards Time Series Generation Conditioned on Unstructured Natural Language
by: Woo, Jaeyun, et al.
Published: (2025)

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
by: Kwon, Dahee, et al.
Published: (2025)

Holistic Order Prediction in Natural Scenes
by: Musacchio, Pierre, et al.
Published: (2025)

Improving Editability in Image Generation with Layer-wise Memory
by: Kim, Daneul, et al.
Published: (2025)

Distribution Matching Distillation without Fake Score Network
by: Kim, Youngjoong, et al.
Published: (2026)

Spatial Evaluation of Chironomus plumosus Distribution Around Agricultural Processing Facilities in Response to Climate Change
by: Tae‐Hyeon Kim, et al.
Published: (2025)

Development of Marine‐Degradable Poly(Ester Amide)s with Strong, Up‐Scalable, and Up‐Cyclable Performance (Adv. Mater. 9/2025)
by: Sung Bae Park, et al.
Published: (2025)

A Dual-Prompting for Interpretable Mental Health Language Models
by: Jeon, Hyolim, et al.
Published: (2024)

Targetless LiDAR-Camera Calibration with Neural Gaussian Splatting
by: Jung, Haebeom, et al.
Published: (2025)

FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables
by: Park, Gunho, et al.
Published: (2025)