Cover Image

Semantic Misalignment in Vision-Language Models under Perceptual Degradation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Cheng, Guo
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

Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models
by: Lee, Jonathan, et al.
Published: (2025)

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
by: Shu, Dong, et al.
Published: (2025)

Probing Perceptual Constancy in Large Vision-Language Models
by: Sun, Haoran, et al.
Published: (2025)

Understanding Degradation with Vision Language Model
by: Lan, Guanzhou, et al.
Published: (2026)

VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression
by: Sargent, Kyle, et al.
Published: (2025)

SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
by: Park, Woohyeon, et al.
Published: (2025)

Detecting Performance Degradation under Data Shift in Pathology Vision-Language Model
by: Guan, Hao, et al.
Published: (2026)

PolarVLM: Bridging the Semantic-Physical Gap in Vision-Language Models
by: Li, Yuliang, et al.
Published: (2026)

ViThinker: Active Vision-Language Reasoning via Dynamic Perceptual Querying
by: You, Weihang, et al.
Published: (2026)

MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
by: Shi, Hao, et al.
Published: (2025)

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
by: Zhu, Xingyu, et al.
Published: (2026)

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
by: Yang, Jiabing, et al.
Published: (2025)

Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts
by: Nooralahzadeh, Farhad, et al.
Published: (2026)

Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
by: Zhang, Yanan, et al.
Published: (2024)

Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models
by: Lu, Jiaying, et al.
Published: (2023)

Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations
by: Shen, Jinjie, et al.
Published: (2025)

Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity
by: Dong, Shuai, et al.
Published: (2025)

AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
by: Ge, Jiannan, et al.
Published: (2024)

Guiding Diffusion Models with Semantically Degraded Conditions
by: Han, Shilong, et al.
Published: (2026)

CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment
by: Shao, Maoyuan, et al.
Published: (2026)

Vision-Language Models vs Human: Perceptual Image Quality Assessment
by: Mehmood, Imran, et al.
Published: (2026)

Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
by: Zhao, Yingying, et al.
Published: (2026)

Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
by: Liu, Jiaqi, et al.
Published: (2025)

HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning
by: Zhang, Zengxi, et al.
Published: (2024)

SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models
by: Zhao, Yifei, et al.
Published: (2026)

SemPT: Semantic Prompt Tuning for Vision-Language Models
by: Shi, Xiao, et al.
Published: (2025)

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models
by: Qi, Jianing, et al.
Published: (2025)

A Multimodal Recaptioning Framework to Account for Perceptual Diversity Across Languages in Vision-Language Modeling
by: Buettner, Kyle, et al.
Published: (2025)

Degradation-Aware Image Enhancement via Vision-Language Classification
by: Cai, Jie, et al.
Published: (2025)

Vision Transformers with Natural Language Semantics
by: Kim, Young Kyung, et al.
Published: (2024)

Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment
by: Hu, Yang, et al.
Published: (2025)

Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
by: Hu, Chengyin, et al.
Published: (2026)

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
by: An, Xiang, et al.
Published: (2026)

Toward Semantic-Agnostic and Shape-Aware Vision-Language Segmentation Models
by: Seutin, Corentin, et al.
Published: (2026)

Training-Free Semantic Multi-Object Tracking with Vision-Language Models
by: Bonat, Laurence, et al.
Published: (2026)

Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise
by: Gao, Yansheng, et al.
Published: (2025)

Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
by: Yang, Haobo, et al.
Published: (2025)

Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment
by: Hernández-Cámara, Pablo, et al.
Published: (2025)

Semantics-aware Motion Retargeting with Vision-Language Models
by: Zhang, Haodong, et al.
Published: (2023)

SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression
by: Zhang, Jiaqian, et al.
Published: (2026)