Large Vision-Language Models

Also known as LVLM

Large vision-language models combine a visual encoder with a language model, aligning them through feature projection, multimodal pretraining, and instruction tuning. Researchers improve their abilities with reinforcement learning, latent visual reasoning, and tools for grounding answers in image regions, especially in visual question answering, OCR, charts, and long-video understanding. To cut inference costs, methods prune visual tokens, select frames, or inspect high-resolution images selectively; other work targets hallucinations, bias, privacy, and adversarial vulnerabilities through data curation, attention interventions, and model editing. Performance is improving across many benchmarks, but reliable fine-grained spatial and temporal reasoning remains difficult, and fluent answers do not always reflect correct use of visual evidence.

Latest papers

404 papers44 papers in the last four weeks, up 63% on the four weeks before. 0.3% of all new papers.

CrystaL: Spontaneous Emergence of Visual Latents in MLLMs
Feb 24, 2026Yang Zhang, Danyang Li, Yuxuan Li +4Vision-Language Models Large Vision-Language Models
VCIP, School of Computer Science, Nankai University · Xiamen University · Nankai International Advanced Research Institute (Shenzhen Futian)
Diagnosing Causal Reasoning in Vision-Language Models via Structured Relevance Graphs
Feb 24, 2026Dhita Putri Pratama, Soyeon Caren Han, Yihao DingVLM Reasoning VLM Evaluation
University of Melbourne Melbourne, Australia · The University of Western Australia Perth, Australia
Vision-Language Models for Ergonomic Assessment of Manual Lifting Tasks: Estimating Horizontal and Vertical Hand Distances from RGB Video
Feb 24, 2026Mohammad Sadra Rajabi, Aanuoluwapo Ojelade, Sunwook Kim +1Large Vision-Language Models
Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg VA 24061, USA · St. Jude Children's Research Hospital, Memphis, TN 38105, USA
VALD: Multi-Stage Vision Attack Detection for Efficient LVLM Defense
Feb 23, 2026Nadav Kadvil, Malak Fares, Ayellet TalVLM Robustness Large Vision-Language Models
Technion – Israel Institute of Technology
Decoupling Vision and Language: Codebook Anchored Visual Adaptation
Feb 23, 2026Jason Wu, Tianchen Zhao, Chang Liu +7VLM Adaptation Large Vision-Language Models
AWS · University of California, Los Angeles
FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery
Feb 22, 2026Xiaokun Zhang, Yi Yang, Ziqi Ye +6Vision-Language Models Remote Sensing Image Understanding
Discipline and Technology Center of Microwave Vision Intelligent Sensing, Fudan University · Shanghai Innovation Institute
HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model Editing
Feb 21, 2026Ahmed Akl, Abdelwahed Khamis, Ali Cheraghian +3Object Hallucination in VLMs VLM Hallucination Mitigation
School of Information and Communication Technology, Griffith University, Australia · Data61, CSIRO, Australia · School of Engineering, Macquarie University, Sydney, Australia
Tuning Qwen2.5-VL to Improve Its Web Interaction Skills
Feb 20, 2026Alexandra Yakovleva, Henrik Pärssinen, Harri Valpola +2PEFT of VLMs Web Agents
Aalto University Espoo, Finland · System 2 AI Helsinki, Finland · University of Oulu Oulu, Finland
OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models
Feb 20, 2026Ling Lin, Yang Bai, Heng Su +5VLM Evaluation VLM Robustness
School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230000, China · Suzhou Institute for Advanced Research, USTC, Suzhou 215123, China · Institute of High Performance Computing (IHPC), A*STAR, Singapore +1
Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
Feb 19, 2026Xiaohan Zhao, Zhaoyi Li, Yaxin Luo +2Adversarial Attacks on VLMs Black-Box Adversarial Attacks
VILA Lab, Department of Machine Learning, MBZUAI
Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
Feb 19, 2026Seulbi Lee, Sangheum HwangVision-Language Models Large Vision-Language Models
Department of Data Science, Seoul National University of Science and Technology, Seoul, Republic of Korea. · Currently with Tomocube, Daejeon, Republic of Korea.
Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing
Feb 18, 2026Jinsong Li, Xiaoyi Dong, Yuhang Zang +3Chart Understanding Fine-Grained Visual Perception
The Chinese University of Hong Kong · Shanghai AI Laboratory · Shanghai Innovation Institute +1
IRIS: Intent Resolution via Inference-time Saccades for Open-Ended VQA in Large Vision-Language Models
Feb 18, 2026Parsa Madinei, Srijita Karmakar, Russell Cohen Hoffing +2Visual Question Answering Large Vision-Language Models
Department of Computer Science, UC Santa Barbara · Department of Psychological & Brain Sciences, UC Santa Barbara · DEVCOM Army Research Laboratory
Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs
Feb 17, 2026Guangtao Lyu, Qi Liu, Chenghao Xu +5Attention Intervention in VLMs VLM Hallucination Mitigation
School of Electronic Engineering, Xidian University, Xi’an, China · College of Computer and Information, Hohai University, Nanjing, China · School of Computer Science and Technology, Xidian University, Xi’an, China +1
Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models
Feb 16, 2026In Chong Choi, Jiacheng Zhang, Feng Liu +1Adversarial Attacks on VLMs Large Vision-Language Models
The University of Melbourne · The University of Adelaide
AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models
Feb 10, 2026Yue Li, Xin Yi, Dongsheng Shi +3Large Vision-Language Models Robust Watermarking
East China Normal University Shanghai, China · Hasso Plattner Institute Potsdam, Germany · University of Potsdam Potsdam, Germany +1
Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures
Feb 8, 2026Simiao Ren, Xingyu Shen, Ankit Raj +8Large Vision-Language Models VLM Evaluation
Manlin · Reality Inc. · New York University +2
SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
Feb 6, 2026Niccolo Avogaro, Nayanika Debnath, Li Mi +6Visual Question Answering Efficient VLM Inference
ETH Zürich · IBM Research · MIT-IBM Watson AI Lab.
Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
Feb 4, 2026Jaehyun Kwak, Nam Cao, Boryeong Cho +3Adversarial Attacks on VLMs Adversarial Attacks
KAIST · KENTECH
A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions
Jan 30, 2026Ji Zhou, Yilin Ding, Yongqi Zhao +4VLM Evaluation Large Vision-Language Models
Institute of Automotive Engineering, Graz University of Technology, 8010 Graz, Austria · Independent Researcher, 200000 Shanghai, China · School of Intelligent Connected Vehicle, Hubei University of Automotive Technology, 442002 Shiyan, China +1
PixSearch: Region-Grounded Retrieval for Knowledgeable Large Multimodal Models
Jan 27, 2026Jeonghwan Kim, Renjie Tao, Sanat Sharma +8Multimodal RAG Visual Question Answering
Meta Reality Labs · University of Illinois Urbana-Champaign
R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation
Jan 25, 2026Zhuohong Chen, Zhengxian Wu, Zirui Liao +6Multimodal RAG Visual Question Answering
1The Shenzhen International Graduate School, Tsinghua University, China · School of Computer Science and Information Engineering, Hefei University of Technology, China · 2State Key Laboratory of Nuclear Power Safety Technology and Equipment, China
From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
Jan 15, 2026Cheng Chen, Yuyu Guo, Pengpeng Zeng +4Vision-Language Models VLM Adaptation
Tongji University, China · Ant Group, China · Shanghai Innovation Institute, China +1
From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection
Dec 17, 2025Manuel Nkegoum, Minh-Tan Pham, Élisa Fromont +2VLM Adaptation Multispectral Object Detection
Univ Bretagne Sud, IRISA, UMR 6074, Vannes, France · ATERMES, Montigny-le-Bretonneux, France · Univ Rennes, IRISA, UMR 6074, Rennes, France +1
Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes
Dec 16, 2025Joseph Hoche, Andrei Bursuc, David Brellmann +4Vision-Language Models Uncertainty Quantification
AMIAD, Pôle Recherche, Palaiseau · Safran Tech · University of Liège +3
Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation
Dec 11, 2025Duo Zheng, Shijia Huang, Yanyang Li +1KV Caching Efficient VLM Inference
The Chinese University of Hong Kong · Weitu AI
Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
Dec 10, 2025Tian Liu, Anwesha Basu, James Caverlee +1Large Vision-Language Models Multimodal Large Language Models
Department of Computer Science and Engineering, Texas A&M University · Department of AI, University of Macau
From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering
Nov 14, 2025Yu Zhao, Ying Zhang, Xuhui Sui +4Visual Question Answering CoT Distillation
College of Computer Science, VCIP, DISSec, Nankai University, Tianjin, China · School of Software, Tiangong University, Tianjin, China · Shenzhen Campus of Sun Yat-sen University, Shenzhen, China +1
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
Nov 2, 2025Shijie Zhou, Viet Dac Lai, Hao Tan +4Multimodal Grounding GUI Grounding
University at Buffalo, USA · Adobe Research, USA
Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
Oct 7, 2025Ryan Solgi, Parsa Madinei, Jiayi Tian +4Model Compression LLM Compression
University of California-Santa Barbara, USA · Amazon, USA

Feb 24, 2026J/K move · Enter open · S save

CrystaL: Spontaneous Emergence of Visual Latents in MLLMs

Yang Zhang, Danyang Li, Yuxuan Li, Xin Zhang+3

VCIP, School of Computer Science, Nankai University · Xiamen University · Nankai International Advanced Research Institute (Shenzhen Futian)

Vision-Language Models Large Vision-Language Models Latent Visual Reasoning Latent CoT Reasoning

Open paper AskPDF arXiv

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in continuous hidden states, facilitating seamless vision-language integration and faster inference. However, existing heuristically predefined supervision signals in latent CoT provide limited guidance for preserving critical visual information in intermediate latent states. To address this limitation, we propose CrystaL (Crystallized Latent Reasoning), a single-stage framework with two paths to process intact and corrupted images, respectively. By explicitly aligning the attention patterns and prediction distributions across the two paths, CrystaL crystallizes latent representations into task-relevant visual semantics, without relying on auxiliary annotations or external modules. Extensive experiments on perception-intensive benchmarks demonstrate that CrystaL consistently outperforms state-of-the-art baselines, achieving substantial gains in fine-grained visual understanding while maintaining robust reasoning capabilities.