Large Vision Language Models

Follow this topic Ask about this topic

Recent momentum

-44%

58 papers in the last 28 days · 0.9% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

19 new papers

A weekly snapshot of new work published in Large Vision Language Models.

Period ending 2026-09-14

8 new papers

A weekly snapshot of new work published in Large Vision Language Models.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Large Vision Language Models.

862 papers

Latest in Large Vision Language Models

Browse all topics →

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers
May 14, 2026Jakub Grzywaczewski, Dawid Płudowski, Przemysław BiecekVision-Language Large Vision Language Models
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
May 14, 2026Hanbo Cheng, Limin Lin, Ruo Zhang +2Visual Generation Text-To-Image
Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study
May 14, 2026Marta Robledo-Moreno, Ruben Vera-Rodriguez, Ruben Tolosana +1Online Signature Verification Large Vision Language Models
MiVE: Multiscale Vision-language features for reference-guided video Editing
May 14, 2026Tong Wang, Meng Zou, Chengjing Wu +4Video Editing Vision Encoders
Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
May 14, 2026Tian Qin, Junzhe Chen, Yuqing Shi +3Large Language Model Hallucination Contrastive Decoding
Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models
May 14, 2026Sujung Hong, Chanyong Yoon, Seong Jae HwangLarge Vision Language Models Explicit Visual Grounding
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
May 14, 2026Chengshuai Zhao, Zhen Tan, Dawei Li +2Harmful Fine-Tuning Large Vision Language Models
CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
May 13, 2026Amirreza Mohseni, Mona Mohammadi, Morteza Saghafian +1Visual Reasoning Curves
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
May 13, 2026Hao Sun, Zi-Jun Ding, Da-Wei ZhouDomain Incremental Learning Spatial Patching
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
May 13, 2026Zhaowei Wang, Lishu Luo, Haodong Duan +9Efficient Long-Context Inference Large Vision Language Models
CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning
May 13, 2026Tengda Guo, Jie Leng, Hanlei Li +6Visual Reasoning Visual Evidence
Test-Time Hinting for Black-Box Vision-Language Models
May 13, 2026Kaihua Hou, Abhijith Varma Mudunuri, Jiaxing Qiu +3Large Vision Language Models Test Time
INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference
May 13, 2026Ahmed Šabanović, Paul Joe Maliakel, Ivona BrandićReal-Time Inference Large Vision Language Models
GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models
May 13, 2026Mingzhe Huang, Weijun Wang, Xin Ding +7Visual Token Pruning Large Vision Language Models
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
May 13, 2026Sangin Lee, Yukyung ChoiVisual Token Pruning Visual Tokens
Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention
May 12, 2026Hamza Ahmed Durrani, Rafay Suleman DurraniLarge Vision Language Models Cross-Modal Alignment
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
May 12, 2026Haiwen Diao, Penghao Wu, Hanming Deng +55Unified Multimodal Models Large Vision Language Models
LychSim: A Controllable and Interactive Simulation Framework for Vision Research
May 12, 2026Wufei Ma, Chloe Wang, Siyi Chen +3Large Vision Language Models Autonomous Driving Simulation
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
May 12, 2026Xiaosong Jia, Bowen Yang, Zuhao Ge +17Large Vision Language Models Task-Relevant Evidence
Towards Automated Air Traffic Safety Assessment Around Non-Towered Airports Using Large Language Models
May 12, 2026Torsten Darrell, Mahyar Ghazanfari, Jordan Kam +3Large Language Model Safety Safety
VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference
May 12, 2026Hao Zhu, Shuo Jin, Wenbin Liao +4Large Vision Language Models Fine-Grained Perception
UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs
May 12, 2026Shuo Ni, Tong Wang, Jing Zhang +4Cloud-Aware Earth Observation Sequences Large Vision Language Models
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
May 12, 2026Chenfeng Wang, Wei He, Xuhan Zhu +10Latent Visual Reasoning Large Vision Language Models
Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
May 12, 2026Boyang Guo, Liang Li, Lin Peng +3Prompt Tuning Large Vision Language Models
Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
May 12, 2026Zhenxin Qin, Qiang Li, Qingzhuo Wang +3Large Vision Language Models Hallucinations
Urban Risk-Aware Navigation via VQA-Based Event Maps for People with Low Vision
May 12, 2026Antoni Valls, Jordi Sanchez-RieraVision-Language Navigation Accessibility
Allegory of the Cave: Measurement-Grounded Vision-Language Learning
May 12, 2026Kepeng Xu, Li Xu, Gang He +1Large Vision Language Models Vision-Language Model Grounding
Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances
May 12, 2026Qirui Wang, Jingyi He, Yining Pan +2Affordances Large Vision Language Models
SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images
May 12, 2026Zishan Liu, Ruoxi Zang, Yanglin Zhang +53D Spatial Reasoning Spatial Reasoning
20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone
May 12, 2026DatologyAI, :, Siddharth Joshi +32Large Vision Language Models Data-Curation
Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?
May 11, 2026Maximilian Triebel, Marco Menner, Dominik HelfensteinPuzzle Large Vision Language Models
Don't Look at the Numbers: Visual Anchoring Bias and Layer-wise Representation in VLMs
May 11, 2026M. ShalankinLarge Vision Language Models Representation Quality
Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking
May 11, 2026Reza Khanmohammadi, Erfan Miahi, Simerjot Kaur +4Large Vision Language Models Explicit Visual Grounding
Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
May 11, 2026Jianzhu Bao, Haozhen Zhang, Kuicai Dong +5Counterfactual Learning Chart
Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition
May 11, 2026David F. Ramirez, Tim L. Overman, Kristen Jaskie +2Synthetic Aperture Radar Large Vision Language Models
C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving
May 11, 2026Kefei Tian, Yuansheng Lian, Kai Yang +2Autonomous Driving Efficient Vision-Language-Action Models
Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
May 11, 2026Qingxin Xiao, Peilin Zhao, Yangyang Zhao +2Large Vision Language Models Large Language Model Hallucination
LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models
May 11, 2026Nikolaos Gkalelis, Vasileios MezarisKnowledge Distillation Large Vision Language Models
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
May 11, 2026Yangneng Chen, Junlin Li, Weijun Yao +4Large Vision Language Models Hallucination Mitigation
SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
May 11, 2026Chen Zhong, Xiao An, Jiaxing Sun +3Remote Sensing Visual Perception
DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
May 11, 2026Lingjun Zhang, Changjie Wu, Linzhe Shi +6Autonomous Driving Large Vision Language Models
AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation
May 11, 2026Xi Jiang, Yinjie Zhao, Zesheng Yang +1Anomalous Frame Detection Large Vision Language Models
Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation
May 11, 2026Yujia Cai, Boxuan Li, Chenghao Xu +1Large Vision Language Models Retrievers
Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models
May 11, 2026Minh Khoi Nguyen, Dai Lam Le, Amir Reza Jafari +8Medical Vision-Language Models Robust Hallucination Detection
The Gordian Knot for VLMs: Diagrammatic Knot Reasoning as a Hard Benchmark
May 11, 2026Hao Liu, Jicheng LiuLarge Vision Language Models Knots
When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
May 11, 2026Chen Li, Zhantao Yang, Fangyi Chen +3Large Vision Language Models Vision-Language
Fashion Florence: Fine-Tuning Florence-2 for Structured Fashion Attribute Extraction
May 11, 2026Anushree BerliaLarge Vision Language Models Low-Rank Adaptation
Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
May 10, 2026Alaa Asfour, Christopher Indris, Leihan Chen +23D Spatial Reasoning Spatial Reasoning
Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
May 10, 2026Jie Ma, Yihang Liu, Zhike Qiu +2Visual Token Pruning Large Vision Language Models
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
May 10, 2026Runze Ma, Shunbo Jia, Haonan Lyu +2Medical Visual Question Answering Textvqa
Language-Conditioned Visual Grounding with CLIP Multilingual
May 9, 2026J. de Curtò, Mauro Liz, I. de ZarzàLarge Vision Language Models Vision-Language Model Grounding
How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A
May 9, 2026YiJie Huang, Yiqun Zhang, Zhuoyue Jia +7Visual Token Pruning Visual Tokens
ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
May 9, 2026Yanbin Hu, Jin Cui, Jiayi Lu +6Vision-Language-Action Models Long-Horizon Planning
DAPE: Dynamic Non-uniform Alignment and Progressive Detail Enhancement Techniques for Improving the Performance of Efficient Visual Language Models
May 9, 2026Mengyuan Tian, Qiyan Zhao, Yanan Wang +1Cross-Modal Alignment Large Vision Language Models
Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution
May 9, 2026Jongseok Park, Sunga Kim, Zhenyu Gu +2Sparse Expert Activation Mixture-of-Experts Models
ZAYA1-VL-8B Technical Report
May 8, 2026Hassan Shapourian, Kasra Hejazi, Olabode M. Sule +1Large Vision Language Models Vision Encoders
Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models
May 8, 2026Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan +1Remote Sensing Urban Environments
GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
May 8, 2026Brown Ebouky, Gabriele Carrino, Niccolo Avogaro +3Large Vision Language Models Multimodal Reasoning
PolarVLM: Bridging the Semantic-Physical Gap in Vision-Language Models
May 8, 2026Yuliang Li, Chu Zhou, Heng Guo +3Large Vision Language Models Polarization
Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs
May 8, 2026Song Zhang, Yanlong Chen, Yilin Li +4Remote Sensing Large Vision Language Models

May 14, 2026 · cs.CVJ/K move · Enter open · S save

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers

Jakub Grzywaczewski, Dawid Płudowski, Przemysław Biecek

Warsaw University of Technology · Centre for Credible Artificial Intelligence · University of Warsaw

Contrastively pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors. Yet, their shared latent spaces are prone to structural anomalies and act as repositories for non-semantic, multi-modal noise. To address this phenomenon, we employ spectral decomposition of covariance matrices to decompose the VLM latent space into a multi-modal semantic signal component and a shared noise subspace. We observe that this noise geometry exhibits strong subgroup invariance across distinct data subsets. Crucially, pruning these shared noise dimensions is mainly harmless, preserving or actively improving downstream task performance. By isolating true semantic signals from artifactual noise, this work provides new mechanistic insights into the representational structure of modern VLMs, suggesting that a substantial fraction of their latent geometry is governed by shared, architecture-level noise rather than task-relevant semantics alone.

Vision-Language Large Vision Language Models Transformer Architectures Representational Capacity Covariance Estimation

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

19 new papers

8 new papers

6 new papers

Latest in Large Vision Language Models