Cover Image

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Saini, Harshvardhan, Jha, Samyak, Tang, Yiming, Liu, Dianbo
Format:	Preprint
Published:	2026
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

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

Safety Alignment for Vision Language Models
by: Liu, Zhendong, et al.
Published: (2024)

When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
by: Yan, Yuping, et al.
Published: (2025)

Seeing the Abstract: Translating the Abstract Language for Vision Language Models
by: Talon, Davide, et al.
Published: (2025)

A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
by: Jung, Hoin, et al.
Published: (2024)

Tuning Vision-Language Models with Candidate Labels by Prompt Alignment
by: Zhang, Zhifang, et al.
Published: (2024)

Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
by: Zhan, Yufei, et al.
Published: (2025)

CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models
by: Jha, Samyak, et al.
Published: (2026)

When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
by: Lu, Hui, et al.
Published: (2025)

Enhance Vision-Language Alignment with Noise
by: Huang, Sida, et al.
Published: (2024)

Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
by: Song, Fei, et al.
Published: (2025)

On the Cultural Anachronism and Temporal Reasoning in Vision Language Models
by: Ranjan, Mukul, et al.
Published: (2026)

AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning
by: Song, Fei, et al.
Published: (2025)

Subspace Alignment for Vision-Language Model Test-time Adaptation
by: Zeng, Zhichen, et al.
Published: (2026)

Learning to Look: Cognitive Attention Alignment with Vision-Language Models
by: Yang, Ryan L., et al.
Published: (2025)

Token-Level Inference-Time Alignment for Vision-Language Models
by: Chen, Kejia, et al.
Published: (2025)

Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models
by: Zhao, Dachuan, et al.
Published: (2025)

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
by: Guimard, Quentin, et al.
Published: (2026)

When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models
by: Yakun, Cui, et al.
Published: (2026)

Training-Free Unsupervised Prompt for Vision-Language Models
by: Long, Sifan, et al.
Published: (2024)

TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
by: Liu, Qinying, et al.
Published: (2023)

SLIP: Structural-aware Language-Image Pretraining for Vision-Language Alignment
by: Lu, Wenbo
Published: (2025)

Enhancing Medical Large Vision-Language Models via Alignment Distillation
by: Chang, Aofei, et al.
Published: (2025)

Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
by: Liu, Junming, et al.
Published: (2026)

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

BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models
by: Gupta, Sunny, et al.
Published: (2026)

When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models
by: Ortu, Francesco, et al.
Published: (2025)

CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models
by: Anand, Neeraj, et al.
Published: (2026)

Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models
by: Yu, Bo, et al.
Published: (2026)

Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
by: Chen, Jun, et al.
Published: (2024)

All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment
by: Zhang, Chunhui, et al.
Published: (2023)

GameVerse: Can Vision-Language Models Learn from Video-based Reflection?
by: Zhang, Kuan, et al.
Published: (2026)

Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models
by: Lian, Chenyu, et al.
Published: (2025)

Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment
by: Kuhn, Lukas, et al.
Published: (2026)

Information-Theoretic Constraints for Continual Vision-Language-Action Alignment
by: Zhao, Libang, et al.
Published: (2026)

VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
by: Zhang, Jianke, et al.
Published: (2026)

When Visuals Aren't the Problem: Evaluating Vision-Language Models on Misleading Data Visualizations
by: Lalai, Harsh Nishant, et al.
Published: (2026)

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
by: Liu, Zhendong, et al.
Published: (2024)

Egocentric Bias in Vision-Language Models
by: Wang, Maijunxian, et al.
Published: (2026)

ROSA: Harnessing Robot States for Vision-Language and Action Alignment
by: Wen, Yuqing, et al.
Published: (2025)