# Multimodal Distribution Matching for Vision-Language Dataset Distillation

arXiv: https://arxiv.org/abs/2605.23482 · HTML: https://mlsanity.com/paper/2605.23482/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 89 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 30 of 67)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (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)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Dataset Condensation with Distribution Matching](https://mlsanity.com/paper/2110.04181/) (2021)
- [High-Performance Large-Scale Image Recognition Without Normalization](https://mlsanity.com/paper/2102.06171/) (2021)
- [Selection via Proxy: Efficient Data Selection for Deep Learning](https://mlsanity.com/paper/1906.11829/) (2019)
- [Dataset Condensation with Differentiable Siamese Augmentation](https://mlsanity.com/paper/2102.08259/) (2021)
- [GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training](https://mlsanity.com/paper/2103.00123/) (2021)
- [Dataset Meta-Learning from Kernel Ridge-Regression](https://mlsanity.com/paper/2011.00050/) (2020)
- [GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning](https://mlsanity.com/paper/2012.10630/) (2020)
- [Dataset Distillation with Infinitely Wide Convolutional Networks](https://mlsanity.com/paper/2107.13034/) (2021)
- [Dataset Condensation via Efficient Synthetic-Data Parameterization](https://mlsanity.com/paper/2205.14959/) (2022)
- [Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory](https://mlsanity.com/paper/2211.10586/) (2022)
- [Dataset Distillation using Neural Feature Regression](https://mlsanity.com/paper/2206.00719/) (2022)
- [Adversarial Active Learning for Deep Networks: a Margin Based Approach](https://mlsanity.com/paper/1802.09841/) (2018)
- [Active Learning by Acquiring Contrastive Examples](https://mlsanity.com/paper/2109.03764/) (2021)
- [DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning](https://mlsanity.com/paper/2204.08499/) (2022)

## Built on by (most cited first, 3 of 3)

- [Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation](https://mlsanity.com/paper/2606.20196/) (2026)
- [Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation](https://mlsanity.com/paper/2606.29464/) (2026)
- [When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models](https://mlsanity.com/paper/2609.35272/) (2026)

## Abstract (arXiv)

Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve representation quality and cross-modal alignment under tight compute and memory budgets, yet prior methods often require heavy computes and overlook their correlations. To address this, we present Multimodal Distribution Matching (MDM), a geometry-aware framework for efficient and generalizable multimodal distillation. Specifically, MDM integrates complementary components at the data, model, and loss levels. At the data level, it initializes synthetic image-text pairs by sampling from clusters in the joint embedding space. At the model level, it forms a mixed teacher by interpolating independently fine-tuned models in weight space according to their angular deviation from the pretrained anchor. At the loss level, it matches joint distributions on the unit hypersphere using a geometry-aware matching objective that exploits the joint features in the cross-modal agreement and discrepancy directions along with symmetric contrastive learning. Across image-text retrieval benchmarks with cross-architecture evaluation, MDM yields compact synthetic sets that preserve multimodal semantics, substantially reduce distillation cost, and remain robust across architectures.