# X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation

arXiv: https://arxiv.org/abs/2610.13687 · HTML: https://mlsanity.com/paper/2610.13687/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 49 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Dataset Condensation with Distribution Matching](https://mlsanity.com/paper/2110.04181/) (2021)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Dataset Condensation with Differentiable Siamese Augmentation](https://mlsanity.com/paper/2102.08259/) (2021)
- [Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory](https://mlsanity.com/paper/2211.10586/) (2022)
- [The Sound of Motions](https://mlsanity.com/paper/1904.05979/) (2019)
- [Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective](https://mlsanity.com/paper/2306.13092/) (2023)
- [Privacy for Free: How does Dataset Condensation Help Privacy?](https://mlsanity.com/paper/2206.00240/) (2022)
- [A Comprehensive Survey of Dataset Distillation](https://mlsanity.com/paper/2301.05603/) (2023)
- [Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data](https://mlsanity.com/paper/1912.07768/) (2019)
- [Data Distillation: A Survey](https://mlsanity.com/paper/2301.04272/) (2023)
- [DataDAM: Efficient Dataset Distillation with Attention Matching](https://mlsanity.com/paper/2310.00093/) (2023)
- [A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition](https://mlsanity.com/paper/2203.14779/) (2022)
- [Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment](https://mlsanity.com/paper/2409.17612/) (2024)
- [The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions](https://mlsanity.com/paper/2502.05673/) (2025)

## Abstract (arXiv)

Audio-visual dataset distillation aims to synthesize a small dataset from a large paired audio-visual dataset, while nearly preserving the training utility for neural networks. Existing approaches such as DM and AVDD face two critical limitations: 1) they are memory-intensive, making them difficult to scale to complex architectures and higher samples-per-class (SPC) settings, and 2) they often fail to preserve strong cross-modal semantic correspondence. To tackle these issues, we propose X-AVDD, a cross-attention-based distillation method that explicitly captures inter-modal relationships during synthesis. By decoupling cross-modal alignment from joint optimization, X-AVDD is substantially more memory-efficient, reducing end-to-end synthesis cost by ~ 8× GPU-hours, while producing highly aligned synthetic data. Empirically, X-AVDD significantly outperforms other audio-visual distillation methods. On VGGSound, an audio-visual dataset of short YouTube clips, X-AVDD improves top-1 test accuracy from 8.2%rightarrow24.0% at SPC=10 and 9.8%rightarrow26.5% at SPC=20. Furthermore, X-AVDD improves cross-architecture generalization (e.g., 25.5%rightarrow35.3% for a ViT target on AVE dataset at SPC =50) and successfully scales to complex architectures such as AudioCLIP, achieving 62.3% accuracy using only 5.65% of the full dataset, against the full dataset accuracy of 72.4% while completing in 9× lower training time compared to the full dataset.