# OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

arXiv: https://arxiv.org/abs/2607.23855 · HTML: https://mlsanity.com/paper/2607.23855/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [Diffusion Transformers with Representation Autoencoders](https://mlsanity.com/paper/2510.11690/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation](https://mlsanity.com/paper/2212.09478/) (2022)
- [REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers](https://mlsanity.com/paper/2504.10483/) (2025)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [UniTok: A Unified Tokenizer for Visual Generation and Understanding](https://mlsanity.com/paper/2502.20321/) (2025)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [Synchformer: Efficient Synchronization from Sparse Cues](https://mlsanity.com/paper/2401.16423/) (2024)
- [JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization](https://mlsanity.com/paper/2503.23377/) (2025)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [What matters for Representation Alignment: Global Information or Spatial Structure?](https://mlsanity.com/paper/2512.10794/) (2025)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation](https://mlsanity.com/paper/2508.16930/) (2025)
- [AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation](https://mlsanity.com/paper/2406.07686/) (2024)
- [Cross-Modal Discrete Representation Learning](https://mlsanity.com/paper/2106.05438/) (2021)
- [Towards Scalable Pre-training of Visual Tokenizers for Generation](https://mlsanity.com/paper/2512.13687/) (2025)

## Abstract (arXiv)

Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly generating audio and video with fine-grained cross-modal correspondence remains challenging due to their fundamental structural differences. Most existing methods use audio and video VAEs trained separately. As a result, the two latent spaces lack cross-modal alignment, leaving the downstream generative model to learn cross-modal synchronization from scratch. We present OmniVAE, a jointly trained audio-video VAE that learns fine-grained semantic alignment between audio and video latent representations. Beyond reconstruction, OmniVAE uses a segment-level audio-video contrastive objective to capture temporal-semantic correspondence and align the two latent spaces. In parallel, it distills features from pretrained modality-specific semantic encoders into each modality, improving the downstream learnability of both latent spaces. Extensive experiments show that both objectives consistently improve the learnability of the latent spaces, translating into higher generation quality and more accurate cross-modal synchronization in downstream text-to-audio-video generation. These findings underscore the importance of learning unified representations as a foundation for omnimodal modeling.1