mlsanityData to 7 Oct 2026

MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

arXiv 2402.03766 ↗First posted 6 Feb 2024cs.CV cs.AIcited by 172

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/MobileVLM .

Key facts. Cited by 172 papers in the map (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 57 of its 68 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

57 of 68 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise19 Dec
  2. 2023Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models11 Dec
  3. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond24 Aug
  4. 2023LISA: Reasoning Segmentation via Large Language Model1 Aug

Other references · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2023Segment Anythingcited by 8,158
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  10. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  11. 2023Qwen Technical Reportcited by 3,273
  12. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
38 more
  1. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  2. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  3. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  4. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  5. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  6. 2019Towards VQA Models That Can Readcited by 1,696
  7. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  8. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  9. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  10. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  11. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  12. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,090
  13. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  14. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  15. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
  16. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 891
  17. 2022Galactica: A Large Language Model for Sciencecited by 736
  18. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  19. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  20. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 510
  21. 2021Unifying Vision-and-Language Tasks via Text Generationcited by 411
  22. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  23. 2016Visual Dialogcited by 377
  24. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  25. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  26. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 298
  27. 2022Visual Spatial Reasoningcited by 288
  28. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 277
  29. 2013Learning Factored Representations in a Deep Mixture of Expertscited by 275
  30. 2021IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoningcited by 262
  31. 2023Honeybee: Locality-enhanced Projector for Multimodal LLMcited by 195
  32. 2023SVIT: Scaling up Visual Instruction Tuningcited by 161
  33. 2023To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuningcited by 143
  34. 2024LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Modelcited by 128
  35. 2023DetGPT: Detect What You Need via Reasoningcited by 112
  36. 2023VIGC: Visual Instruction Generation and Correctioncited by 80
  37. 2023Norm Tweaking: High-performance Low-bit Quantization of Large Language Modelscited by 33
  38. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 74; 2025: 63; 2026: 35.

172 papers.

Sort:

By area:

  1. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  2. 2024LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Modelscited by 394
  3. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 331
  4. 2024SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generationcited by 328
  5. 2024What matters when building vision-language models?cited by 321
  6. 2024TokenPacker: Efficient Visual Projector for Multimodal LLMcited by 170
  7. 2024Building and better understanding vision-language models: insights and future directionscited by 169
  8. 2024Ovis: Structural Embedding Alignment for Multimodal Large Language Modelcited by 167
  9. 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Tokencited by 164
  10. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 162
  11. 2024LLM Inference Unveiled: Survey and Roofline Model Insightscited by 147
  12. 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Taskscited by 136
38 more
  1. 2024The Revolution of Multimodal Large Language Models: A Surveycited by 134
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  3. 2024Efficient Multimodal Learning from Data-centric Perspectivecited by 120
  4. 2024VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understandingcited by 113
  5. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 108
  6. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 102
  7. 2024On-Device Language Models: A Comprehensive Reviewcited by 101
  8. 2024Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inferencecited by 97
  9. 2024Efficient Multimodal Large Language Models: A Surveycited by 95
  10. 2024Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performancecited by 94
  11. 2024DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Modelscited by 93
  12. 2025UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learningcited by 83
  13. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 83
  14. 2024What If We Recaption Billions of Web Images with LLaMA-3?cited by 82
  15. 2024Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-trainingcited by 82
  16. 2024FastVLM: Efficient Vision Encoding for Vision Language Modelscited by 76
  17. 2025Harmonizing Visual Representations for Unified Multimodal Understanding and Generationcited by 74
  18. 2024I2EBench: A Comprehensive Benchmark for Instruction-based Image Editingcited by 61
  19. 2024Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsificationcited by 59
  20. 2024HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inferencecited by 53
  21. 2024From Pixels to Prose: A Large Dataset of Dense Image Captionscited by 52
  22. 2024CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMscited by 49
  23. 2024Dense Connector for MLLMscited by 48
  24. 2025FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocitiescited by 46
  25. 2024A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicinecited by 45
  26. 2025Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representationscited by 44
  27. 2024LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillationcited by 43
  28. 2024SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Foldingcited by 42
  29. 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detectorcited by 38
  30. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  31. 2025MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantizationcited by 35
  32. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  33. 2024African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classificationcited by 31
  34. 2025Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Modelscited by 30
  35. 2024Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectlycited by 29
  36. 2025Vision-Language Models for Edge Networks: A Comprehensive Surveycited by 29
  37. 2024VisionLLaMA: A Unified LLaMA Backbone for Vision Taskscited by 28
  38. 2024V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encodingcited by 28

50 most cited of 172 All 172 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
  2. 202620/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone
  3. 2025MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning
  4. 2025A Survey on Efficient Vision-Language Models
  5. 2026Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs
  6. 2025From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
  7. 2025EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
  8. 2026DataComp-VLM: Improved Open Datasets for Vision-Language Models