Cover Image

Preserving Localized Patch Semantics in VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Esmaeilkhani, Parsa, Latecki, Longin Jan
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

Direct Visual Grounding by Directing Attention of Visual Tokens
by: Esmaeilkhani, Parsa, et al.
Published: (2025)

Layout Stroke Imitation: A Layout Guided Handwriting Stroke Generation for Style Imitation with Diffusion Model
by: Hanif, Sidra, et al.
Published: (2025)

Learning Object Focused Attention
by: Trivedy, Vivek, et al.
Published: (2025)

VAPO: Visibility-Aware Keypoint Localization for Efficient 6DoF Object Pose Estimation
by: Lian, Ruyi, et al.
Published: (2024)

Enhancing Renal Tumor Malignancy Prediction: Deep Learning with Automatic 3D CT Organ Focused Attention
by: Fan, Zhengkang, et al.
Published: (2026)

FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
by: Pan, Huitong, et al.
Published: (2024)

From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance
by: Aryashad, Ardalan, et al.
Published: (2025)

Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs
by: Lim, Jeongkee, et al.
Published: (2024)

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
by: Xu, Shuhan, et al.
Published: (2025)

Validation of Whole-Slide Foundation Models for Image Retrieval in TCGA Data
by: Lei, Tianhao, et al.
Published: (2026)

VLMs Can Aggregate Scattered Training Patches
by: Zhou, Zhanhui, et al.
Published: (2025)

Teaching VLMs to Localize Specific Objects from In-context Examples
by: Doveh, Sivan, et al.
Published: (2024)

Spotlight: Identifying and Localizing Video Generation Errors Using VLMs
by: Chinchure, Aditya, et al.
Published: (2025)

MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes
by: Liu, Liu, et al.
Published: (2025)

Structure-Preserving Patch Decoding for Efficient Neural Video Representation
by: Hayami, Taiga, et al.
Published: (2025)

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
by: Fang, Zhengyao, et al.
Published: (2026)

Assessing Situational and Spatial Awareness of VLMs with Synthetically Generated Video
by: Benschop, Pascal, et al.
Published: (2026)

Balancing Saliency and Coverage: Semantic Prominence-Aware Budgeting for Visual Token Compression in VLMs
by: Lee, Jaehoon, et al.
Published: (2026)

Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation
by: Wu, Wangyu, et al.
Published: (2024)

SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning
by: Chen, Zhi, et al.
Published: (2025)

Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts
by: Dumpala, Sri Harsha, et al.
Published: (2024)

Adversarial Patch for 3D Local Feature Extractor
by: Pao, Yu Wen, et al.
Published: (2024)

Patch Ranking: Efficient CLIP by Learning to Rank Local Patches
by: Wu, Cheng-En, et al.
Published: (2024)

Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
by: Deng, Wei, et al.
Published: (2025)

Bridging Semantic Logic Gaps: A Cognition Inspired Multimodal Boundary Preserving Network for Image Manipulation Localization
by: Li, Songlin, et al.
Published: (2025)

Deep Pre-Alignment for VLMs
by: Yu, Tianyu, et al.
Published: (2026)

HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion
by: Su, Junhao, et al.
Published: (2024)

Hierarchical Salient Patch Identification for Interpretable Fundus Disease Localization
by: Peng, Yitao, et al.
Published: (2024)

Adversarial Patch Attack for Ship Detection via Localized Augmentation
by: Liu, Chun, et al.
Published: (2025)

PATS: Patch Area Transportation with Subdivision for Local Feature Matching
by: Ni, Junjie, et al.
Published: (2023)

Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction
by: Jain, Riddhi, et al.
Published: (2025)

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
by: Wang, Dianyi, et al.
Published: (2025)

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
by: Shahgir, Haz Sameen, et al.
Published: (2026)

SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
by: Li, Sifan, et al.
Published: (2025)

Context Patch Fusion With Class Token Enhancement for Weakly Supervised Semantic Segmentation
by: Fu, Yiyang, et al.
Published: (2026)

CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation
by: Zhang, Dengke, et al.
Published: (2024)

Are VLMs Really Blind
by: Singh, Ayush, et al.
Published: (2024)

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency
by: Wen, Ziqi, et al.
Published: (2026)

Regression in EO: Are VLMs Up to the Challenge?
by: Xue, Xizhe, et al.
Published: (2025)

GNSP: Gradient Null Space Projection for Preserving Cross-Modal Alignment in VLMs Continual Learning
by: Peng, Tiantian, et al.
Published: (2025)