Cover Image

Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	An, Na Min, Kang, Inha, Lee, Minhyun, Shim, Hyunjung
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
by: Lee, Seonho, et al.
Published: (2025)

Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?
by: Kim, Eunki, et al.
Published: (2025)

How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions
by: An, Na Min, et al.
Published: (2025)

No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather
by: Park, Junsung, et al.
Published: (2025)

Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
by: Choi, Jiho, et al.
Published: (2024)

Interpretable Debiasing of Vision-Language Models for Social Fairness
by: An, Na Min, et al.
Published: (2026)

Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
by: Choi, Jiho, et al.
Published: (2025)

TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation
by: Park, NaHyeon, et al.
Published: (2024)

What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
by: Kang, Inha, et al.
Published: (2025)

Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels
by: Lee, Seungho, et al.
Published: (2024)

SeiT++: Masked Token Modeling Improves Storage-efficient Training
by: Lee, Minhyun, et al.
Published: (2023)

I0T: Embedding Standardization Method Towards Zero Modality Gap
by: An, Na Min, et al.
Published: (2024)

Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models
by: Zhu, Yingjie, et al.
Published: (2025)

MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
by: Lee, Minhyun, et al.
Published: (2024)

Prompt the Unseen: Evaluating Visual-Language Alignment Beyond Supervision
by: Jung, Raehyuk, et al.
Published: (2025)

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
by: Min, Cheolhong, et al.
Published: (2026)

Grounding Driving VLA via Inverse Kinematics
by: Park, Junsung, et al.
Published: (2026)

World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models
by: Kim, Eunsu, et al.
Published: (2025)

Zero-Shot 3D Visual Grounding from Vision-Language Models
by: Li, Rong, et al.
Published: (2025)

Spatial-VLN: Zero-Shot Vision-and-Language Navigation With Explicit Spatial Perception and Exploration
by: Yue, Lu, et al.
Published: (2026)

Rethinking the Use of Vision Transformers for AI-Generated Image Detection
by: Park, NaHyeon, et al.
Published: (2025)

SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation
by: Zhang, Jiwen, et al.
Published: (2026)

Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments
by: Rajiv, Manjunath Prasad Holenarasipura, et al.
Published: (2025)

MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning
by: Liu, Chenghao, et al.
Published: (2025)

Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment
by: Jeong, Seongjun, et al.
Published: (2024)

BiasICL: In-Context Learning and Demographic Biases of Vision Language Models
by: Xu, Sonnet, et al.
Published: (2025)

Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers
by: Pantazopoulos, Georgios, et al.
Published: (2024)

Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
by: Lee, Seungho, et al.
Published: (2024)

Representation Alignment for Just Image Transformers is not Easier than You Think
by: Shin, Jaeyo, et al.
Published: (2026)

MLFM: Multi-Layered Feature Maps for Richer Language Understanding in Zero-Shot Semantic Navigation
by: Raychaudhuri, Sonia, et al.
Published: (2025)

ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models
by: Sural, Shounak, et al.
Published: (2024)

DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models
by: Ryu, Hyogon, et al.
Published: (2025)

SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models
by: Cheng, An-Chieh, et al.
Published: (2024)

Language-Guided Invariance Probing of Vision-Language Models
by: Lee, Jae Joong
Published: (2025)

Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models
by: Ranasinghe, Yasiru, et al.
Published: (2025)

Label-Augmented Dataset Distillation
by: Kang, Seoungyoon, et al.
Published: (2024)

Learning Primitive Relations for Compositional Zero-Shot Learning
by: Lee, Insu, et al.
Published: (2025)

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
by: Huang, Jen-tse, et al.
Published: (2025)

Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models
by: Park, NaHyeon, et al.
Published: (2025)

Vision Language Models are Biased
by: Vo, An, et al.
Published: (2025)