# PaliGemma 2: A Family of Versatile VLMs for Transfer

arXiv: https://arxiv.org/abs/2412.03555 · HTML: https://mlsanity.com/paper/2412.03555/

## Key facts

- Cited by 207 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.
- Builds on 26 of its 112 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [Neural Combinatorial Optimization with Reinforcement Learning](https://mlsanity.com/paper/1611.09940/) (2016)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training](https://mlsanity.com/paper/2403.09611/) (2024)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [PaLI-3 Vision Language Models: Smaller, Faster, Stronger](https://mlsanity.com/paper/2310.09199/) (2023)
- [Advancing Multimodal Medical Capabilities of Gemini](https://mlsanity.com/paper/2405.03162/) (2024)
- [SciCap: Generating Captions for Scientific Figures](https://mlsanity.com/paper/2110.11624/) (2021)
- [MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning](https://mlsanity.com/paper/2409.20566/) (2024)
- [BRAVE: Broadening the visual encoding of vision-language models](https://mlsanity.com/paper/2404.07204/) (2024)
- [GriTS: Grid table similarity metric for table structure recognition](https://mlsanity.com/paper/2203.12555/) (2022)
- [An End-to-End Multi-Task Learning Model for Image-based Table Recognition](https://mlsanity.com/paper/2303.08648/) (2023)
- [Pre-training image-language transformers for open-vocabulary tasks](https://mlsanity.com/paper/2209.04372/) (2022)

## Built on by (most cited first, 30 of 207)

- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model](https://mlsanity.com/paper/2509.09372/) (2025)
- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos](https://mlsanity.com/paper/2510.21571/) (2025)
- [Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning](https://mlsanity.com/paper/2503.18013/) (2025)
- [Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization](https://mlsanity.com/paper/2601.12993/) (2026)
- [Unified Autoregressive Visual Generation and Understanding with Continuous Tokens](https://mlsanity.com/paper/2503.13436/) (2025)
- [TrackVLA: Embodied Visual Tracking in the Wild](https://mlsanity.com/paper/2505.23189/) (2025)
- [GigaBrain-0: A World Model-Powered Vision-Language-Action Model](https://mlsanity.com/paper/2510.19430/) (2025)
- [SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model](https://mlsanity.com/paper/2504.09644/) (2025)
- [VisRL: Intention-Driven Visual Perception via Reinforced Reasoning](https://mlsanity.com/paper/2503.07523/) (2025)
- [VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models](https://mlsanity.com/paper/2601.03309/) (2026)
- [DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies](https://mlsanity.com/paper/2505.07813/) (2025)
- [Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs](https://mlsanity.com/paper/2506.09047/) (2025)
- [Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future](https://mlsanity.com/paper/2512.16760/) (2025)
- [ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries](https://mlsanity.com/paper/2603.12942/) (2026)
- [VISA: Retrieval Augmented Generation with Visual Source Attribution](https://mlsanity.com/paper/2412.14457/) (2024)
- [Mellow: a small audio language model for reasoning](https://mlsanity.com/paper/2503.08540/) (2025)
- [Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.04034/) (2025)
- [Jenga: Effective Memory Management for Serving LLM with Heterogeneity](https://mlsanity.com/paper/2503.18292/) (2025)
- [v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning](https://mlsanity.com/paper/2505.18842/) (2025)
- [ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulation](https://mlsanity.com/paper/2505.09698/) (2025)
- [GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning](https://mlsanity.com/paper/2602.12099/) (2026)
- [Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes](https://mlsanity.com/paper/2504.15037/) (2025)
- [FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization](https://mlsanity.com/paper/2512.04952/) (2025)
- [A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation](https://mlsanity.com/paper/2602.01067/) (2026)

## Abstract (arXiv)

PaliGemma 2 is an upgrade of the PaliGemma open Vision-Language Model (VLM) based on the Gemma 2 family of language models. We combine the SigLIP-So400m vision encoder that was also used by PaliGemma with the whole range of Gemma 2 models, from the 2B one all the way up to the 27B model. We train these models at three resolutions (224px, 448px, and 896px) in multiple stages to equip them with broad knowledge for transfer via fine-tuning. The resulting family of base models covering different model sizes and resolutions allows us to investigate factors impacting transfer performance (such as learning rate) and to analyze the interplay between the type of task, model size, and resolution. We further increase the number and breadth of transfer tasks beyond the scope of PaliGemma including different OCR-related tasks such as table structure recognition, molecular structure recognition, music score recognition, as well as long fine-grained captioning and radiography report generation, on which PaliGemma 2 obtains state-of-the-art results.