Large Vision-Language Models

Also known as LVLM

Overview

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

CardsList

415 papers6 papers in the last four weeks, down 88% on the four weeks before. 0.0% of all new papers.

  1. Subliminal Learning in Vision-Language Models

    Nov 4, 2026Arman Hatami, Romina Aalishah, Ilya E. MonosovLarge Vision-Language ModelsVLM Post-Training

  2. Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models

    Nov 3, 2026Junsung Park, Sangwon Yu, Donghun Kang +6Large Vision-Language ModelsVLM Interpretability

  3. The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models

    Nov 3, 2026Chenyu Yi, Jiawen Zong, Sami Hormi +3Unlearnable ExamplesAdversarial Attacks on VLMs

  4. Entropy-Gated Dynamic Rectification for Object Hallucination in Large Vision-Language Models

    Nov 3, 2026Riasad Alvi, Md. Asaduzzaman Shuvo, Md. Ahashan Habib +1Activation Steering in VLMsObject Hallucination in VLMs

  5. DramaVQA: Probing Detailed Understanding of Ultra-Long TV Dramas

    Oct 31, 2026Xinyue Huo, Pengfei Chen, Jiannan Ge +5Video UnderstandingLong-Video QA

  6. Zoom Where the Answer Looks: Cross-Resolution Self-Distillation for MLLMs under Visual-Token Budgets

    Oct 23, 2026Zhensheng Hu, Guanglong Xu, Guanqiang HuLarge Vision-Language ModelsVisual Evidence Sensitivity in VLMs

  7. CatchUp: Depth-Aware Re-Admission of Visual Tokens for Efficient Large Vision-Language Models

    Oct 16, 2026Eunju Park, Uiwon HwangEfficient VLM InferenceLarge Vision-Language Models

  8. Xiaomi-Lens-0 Technical Report

    Oct 16, 2026Pei Fu, Yike Liu, Yue Sun +13Large Vision-Language ModelsReferring Image Segmentation

  9. SimpleVLN: Towards Simple and Frontier Vision-Language Navigation

    Oct 16, 2026Lingyi Hong, Weiren Cai, Jiayu Chen +7Vision-Language NavigationLarge Vision-Language Models

  10. Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs

    Oct 13, 2026Peiran Yin, Hao Wu, Zihao Yang +6Visual Token PruningEfficient VLM Inference

  11. From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models

    Oct 13, 2026Hyeonggeun Han, Taehyun Cho, Sangwoo HongVLM Hallucination MitigationObject Hallucination in VLMs

  12. COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration

    Oct 12, 2026Damien Lo, Hong Kyu Lee, Ruixuan Liu +1Membership Inference AttacksLarge Vision-Language Models

  13. FoveaTree: Information-Density Trees for Query-Guided Visual Token Pruning in Video Large Language Models

    Oct 12, 2026Zihan Meng, Weidong Chen, Dexiang Hong +2Efficient VLM InferenceVisual Token Pruning

  14. SpatialASM: Internalizing Active Mentalization for Spatial Reasoning

    Oct 9, 2026Yuhong Liu, Shenxi Wu, Junyi Chi +5Visual Spatial ReasoningVisual Reasoning

  15. OWLET: On-Policy Weighted Learning via Evidence Transfer for Video Large Language Model Post-Training

    Oct 9, 2026Qitan Lv, Ke Fan, Hong Wang +5Video-Language ModelsLarge Vision-Language Models

  16. MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph

    Oct 9, 2026Yingjie Zhu, Han Cheng, Xuefeng Bai +3VLM ReasoningVLM Evaluation

  17. Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations

    Oct 8, 2026Shuran Ma, JiaLe Li, Yuxin Dong +9VLM Hallucination MitigationLarge Vision-Language Models

  18. From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment

    Oct 8, 2026Chen Zhao, Xingping Dong, Jiachun Shi +5Object Hallucination in VLMsVLM Hallucination Mitigation

  19. SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders

    Oct 8, 2026Jeonghyo Song, YoungJoon YooAttention Intervention in VLMsVision-Language Grounding

  20. Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions

    Oct 7, 2026Bojun Yang, Haochen Zhou, Zhifang Zhang +3VLM RobustnessLarge Vision-Language Models

  21. Mixture of Layers: Dynamic Layer Routing for Visual Reasoning

    Oct 7, 2026Jeonghwan Kim, Sofia Stoica, Jiwan Chung +5VLM ReasoningLarge Vision-Language Models

  22. Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-Tuning

    Oct 5, 2026Suguru Onda, Matthew Bailey, Ryan FarrellVision-Language ModelsVLM Adaptation

  23. What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization

    Oct 5, 2026Ayesh Abu Lehyeh, Jay Hwasung Jung, Safwan WshahCross-View Geo-LocalizationLarge Vision-Language Models

  24. Fitting Vision Adapters at Frontier Scales

    Oct 5, 2026Jaehoon Lee, Harry Partridge, Mudith Jayasekara +3Vision-Language ModelsVLM Adaptation

  25. IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning

    Oct 4, 2026Jiawen Xi, Yu Zhang, Tianyi Zhao +3Tool Use in VLMsInfrared Small Target Detection

  26. Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency

    Oct 3, 2026Sixun Dong, Wei Li, Andong Deng +4Efficient VLM InferenceLong-Video Understanding