# ViTamin: Designing Scalable Vision Models in the Vision-Language Era

arXiv: https://arxiv.org/abs/2404.02132 · HTML: https://mlsanity.com/paper/2404.02132/

## Key facts

- Cited by 39 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 139 of its 172 references that are in the map.
- First posted on arXiv 2 Apr 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, 30 of 139)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)

## Built on by (most cited first, 30 of 39)

- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation](https://mlsanity.com/paper/2412.03069/) (2024)
- [UniTok: A Unified Tokenizer for Visual Generation and Understanding](https://mlsanity.com/paper/2502.20321/) (2025)
- [3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark](https://mlsanity.com/paper/2412.07825/) (2024)
- [Efficient Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2405.10739/) (2024)
- [FastVLM: Efficient Vision Encoding for Vision Language Models](https://mlsanity.com/paper/2412.13303/) (2024)
- [Efficient Large Multi-modal Models via Visual Context Compression](https://mlsanity.com/paper/2406.20092/) (2024)
- [DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies](https://mlsanity.com/paper/2503.14324/) (2025)
- [SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models](https://mlsanity.com/paper/2505.00788/) (2025)
- [FlowTok: Flowing Seamlessly Across Text and Image Tokens](https://mlsanity.com/paper/2503.10772/) (2025)
- [The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer](https://mlsanity.com/paper/2504.10462/) (2025)
- [Vision-Language Models for Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/2502.07855/) (2025)
- [COCONut: Modernizing COCO Segmentation](https://mlsanity.com/paper/2404.08639/) (2024)
- [X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP](https://mlsanity.com/paper/2505.05528/) (2025)
- [Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model](https://mlsanity.com/paper/2406.19369/) (2024)
- [ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation](https://mlsanity.com/paper/2412.09754/) (2024)
- [Toward a Holistic Evaluation of Robustness in CLIP Models](https://mlsanity.com/paper/2410.01534/) (2024)
- [Region-based Cluster Discrimination for Visual Representation Learning](https://mlsanity.com/paper/2507.20025/) (2025)
- [Classification Done Right for Vision-Language Pre-Training](https://mlsanity.com/paper/2411.03313/) (2024)
- [What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion](https://mlsanity.com/paper/2605.07915/) (2026)
- [Thinking with Spatial Code for Physical-World Video Reasoning](https://mlsanity.com/paper/2603.05591/) (2026)
- [SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking](https://mlsanity.com/paper/2506.02803/) (2025)
- [SuperCLIP: CLIP with Simple Classification Supervision](https://mlsanity.com/paper/2512.14480/) (2025)
- [NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization](https://mlsanity.com/paper/2511.08417/) (2025)
- [Innovative Tooth Segmentation Using Hierarchical Features and Bidirectional Sequence Modeling](https://mlsanity.com/paper/2602.21712/) (2026)
- [DiffCLIP: Differential Attention Meets CLIP](https://mlsanity.com/paper/2503.06626/) (2025)
- [VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings](https://mlsanity.com/paper/2503.06368/) (2025)
- [Foundation Models For Seismic Data Processing: An Extensive Review](https://mlsanity.com/paper/2503.24166/) (2025)
- [Multimodal Representation Learning Conditioned on Semantic Relations](https://mlsanity.com/paper/2508.17497/) (2025)
- [Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation](https://mlsanity.com/paper/2511.01593/) (2025)

## Abstract (arXiv)

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on the large-scale Internet image-text pairs. However, despite the amazing achievement from the VLMs, vanilla Vision Transformers (ViTs) remain the default choice for the image encoder. Although pure transformer proves its effectiveness in the text encoding area, it remains questionable whether it is also the case for image encoding, especially considering that various types of networks are proposed on the ImageNet benchmark, which, unfortunately, are rarely studied in VLMs. Due to small data/model scale, the original conclusions of model design on ImageNet can be limited and biased. In this paper, we aim at building an evaluation protocol of vision models in the vision-language era under the contrastive language-image pretraining (CLIP) framework. We provide a comprehensive way to benchmark different vision models, covering their zero-shot performance and scalability in both model and training data sizes. To this end, we introduce ViTamin, a new vision models tailored for VLMs. ViTamin-L significantly outperforms ViT-L by 2.0% ImageNet zero-shot accuracy, when using the same publicly available DataComp-1B dataset and the same OpenCLIP training scheme. ViTamin-L presents promising results on 60 diverse benchmarks, including classification, retrieval, open-vocabulary detection and segmentation, and large multi-modal models. When further scaling up the model size, our ViTamin-XL with only 436M parameters attains 82.9% ImageNet zero-shot accuracy, surpassing 82.0% achieved by EVA-E that has ten times more parameters (4.4B).