Cover Image

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shahgir, Haz Sameen, Chen, Xiaofu, Fu, Yu, Shayegani, Erfan, Abu-Ghazaleh, Nael, Kementchedjhieva, Yova, Dong, Yue
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Modeling Hierarchical Thinking in Large Reasoning Models
by: Shahariar, G M, et al.
Published: (2025)

The Devil is in the EOS: Sequence Training for Detailed Image Captioning
by: Mohamed, Abdelrahman, et al.
Published: (2025)

SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
by: Chen, Xiaofu, et al.
Published: (2025)

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
by: Shayegani, Erfan, et al.
Published: (2025)

Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs
by: Salazar, Israfel, et al.
Published: (2025)

Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
by: Fu, Yu, et al.
Published: (2025)

IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
by: Shahgir, Haz Sameen, et al.
Published: (2024)

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
by: Bachu, Saketh, et al.
Published: (2024)

ExpertGenQA: Open-ended QA generation in Specialized Domains
by: Shahgir, Haz Sameen, et al.
Published: (2025)

Do Reasoning LLMs Refuse What They Infer in Long Contexts?
by: Fu, Yu, et al.
Published: (2026)

Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
by: Shayegani, Erfan, et al.
Published: (2025)

A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA
by: Shoer, Belal, et al.
Published: (2025)

EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval
by: Huzaifa, Muhammad, et al.
Published: (2024)

Cross-Modal Safety Alignment: Is textual unlearning all you need?
by: Chakraborty, Trishna, et al.
Published: (2024)

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
by: Li, Jiaang, et al.
Published: (2023)

CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented Captioning
by: Ibrahim, George, et al.
Published: (2025)

Answerability in Retrieval-Augmented Open-Domain Question Answering
by: Abdumalikov, Rustam, et al.
Published: (2024)

LLMs Can Compensate for Deficiencies in Visual Representations
by: Takishita, Sho, et al.
Published: (2025)

Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
by: Shahgir, Haz Sameen, et al.
Published: (2023)

Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs
by: Mahfuz, Tamzeed, et al.
Published: (2024)

That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications
by: Slocum, Carter, et al.
Published: (2023)

Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems
by: Zhang, Yicheng, et al.
Published: (2025)

GPUVM: GPU-driven Unified Virtual Memory
by: Nazaraliyev, Nurlan, et al.
Published: (2024)

Connecting the Dots: Leveraging Spatio-Temporal Graph Neural Networks for Accurate Bangla Sign Language Recognition
by: Shahgir, Haz Sameen, et al.
Published: (2024)

Multimodal Large Language Models to Support Real-World Fact-Checking
by: Geng, Jiahui, et al.
Published: (2024)

A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
by: Ruder, Sebastian, et al.
Published: (2018)

Overcoming Vocabulary Constraints with Pixel-level Fallback
by: Lotz, Jonas F., et al.
Published: (2025)

Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
by: Mamun, Md Abdullah Al, et al.
Published: (2025)

LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal Distillation
by: Irawan, Patrick Amadeus, et al.
Published: (2026)

A Real-Time System to Populate FRA Form 57 from News
by: Lim, Chansong, et al.
Published: (2025)

Noise is an Efficient Learner for Zero-Shot Vision-Language Models
by: Imam, Raza, et al.
Published: (2025)

MuLan: A Study of Fact Mutability in Language Models
by: Fierro, Constanza, et al.
Published: (2024)

Co(ve)rtex: ML Models as storage channels and their (mis-)applications
by: Mamun, Md Abdullah Al, et al.
Published: (2023)

Leveraging Complementary Attention maps in vision transformers for OCT image analysis
by: Shahgir, Haz Sameen, et al.
Published: (2023)

Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
by: Fu, Yu, et al.
Published: (2026)

From Measurement to Expertise: Empathetic Expert Adapters for Context-Based Empathy in Conversational AI Agents
by: Shayegani, Erfan, et al.
Published: (2025)

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
by: Zhou, Guanyu, et al.
Published: (2026)

JEEM: Vision-Language Understanding in Four Arabic Dialects
by: Kadaoui, Karima, et al.
Published: (2025)

Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors
by: Shi, Youxu, et al.
Published: (2025)

AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
by: Abir, Abrar Rahman, et al.
Published: (2025)