mlsanityData to 14 Oct 2026

PaliGemma: A versatile 3B VLM for transfer

arXiv 2407.07726 ↗First posted 10 Jul 2024cs.CV cs.AI cs.CLcited by 696

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

Abstract (arXiv)

PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly knowledgeable base model that is effective to transfer. It achieves strong performance on a wide variety of open-world tasks. We evaluate PaliGemma on almost 40 diverse tasks including standard VLM benchmarks, but also more specialized tasks such as remote-sensing and segmentation.

Key facts. Cited by 696 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. First posted on arXiv 10 Jul 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 81; 2025: 322; 2026: 293.

696 papers.

Sort:

By area:

  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  3. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  4. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  5. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  6. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  7. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339
  8. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 329
  9. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  10. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 237
  11. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 221
  12. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
38 more
  1. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 207
  2. 2024Building and better understanding vision-language models: insights and future directionscited by 173
  3. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  4. 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
  5. 2024Multimodal Whole Slide Foundation Model for Pathologycited by 162
  6. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 146
  7. 2024AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmarkcited by 140
  8. 2024Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoderscited by 139
  9. 2026Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Groundingcited by 139
  10. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 139
  11. 2025Unified Vision-Language-Action Modelcited by 134
  12. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 134
  13. 2024Randomized Autoregressive Visual Generationcited by 127
  14. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 123
  15. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 118
  16. 2024Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Modelscited by 116
  17. 2025GR-3 Technical Reportcited by 111
  18. 2025What Can RL Bring to VLA Generalization? An Empirical Studycited by 108
  19. 2025OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoningcited by 107
  20. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Modelscited by 105
  21. 2026A Pragmatic VLA Foundation Modelcited by 103
  22. 2024Benchmarking Vision Language Models for Cultural Understandingcited by 101
  23. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspectivecited by 96
  24. 2024Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performancecited by 94
  25. 2025Galaxea Open-World Dataset and G0 Dual-System VLA Modelcited by 92
  26. 2025ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulationcited by 91
  27. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  28. 2024What Matters in Building Vision-Language-Action Models for Generalist Robotscited by 89
  29. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 86
  30. 2025Describe Anything: Detailed Localized Image and Video Captioningcited by 84
  31. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  32. 2024Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-trainingcited by 82
  33. 2025ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceivercited by 81
  34. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Modelscited by 80
  35. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 80
  36. 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robotscited by 79
  37. 2024FastVLM: Efficient Vision Encoding for Vision Language Modelscited by 77
  38. 2024MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuningcited by 76

50 most cited of 696 All 696 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023PaLI-3 Vision Language Models: Smaller, Faster, Stronger
  2. 2026Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
  3. 2026TranslateGemma Technical Report
  4. 2026Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
  5. 2025RT-VLM: Re-Thinking Vision Language Model with 4-Clues for Real-World Object Recognition Robustness
  6. 2024Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities
  7. 2025Visual Large Language Models for Generalized and Specialized Applications
  8. 2025Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities