# 3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation

arXiv: https://arxiv.org/abs/2511.21780 · HTML: https://mlsanity.com/paper/2511.21780/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 45 of its 49 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation](https://mlsanity.com/paper/2212.09478/) (2022)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [Localizing Visual Sounds the Hard Way](https://mlsanity.com/paper/2104.02691/) (2021)
- [Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners](https://mlsanity.com/paper/2402.17723/) (2024)
- [JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization](https://mlsanity.com/paper/2503.23377/) (2025)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation](https://mlsanity.com/paper/2309.16429/) (2023)
- [Wan-S2V: Audio-Driven Cinematic Video Generation](https://mlsanity.com/paper/2508.18621/) (2025)
- [UniVerse-1: Unified Audio-Video Generation via Stitching of Experts](https://mlsanity.com/paper/2509.06155/) (2025)
- [OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows](https://mlsanity.com/paper/2412.01169/) (2024)
- [HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation](https://mlsanity.com/paper/2508.16930/) (2025)

## Built on by (most cited first, 5 of 5)

- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding](https://mlsanity.com/paper/2604.11244/) (2026)
- [Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer](https://mlsanity.com/paper/2608.15690/) (2026)
- [Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy](https://mlsanity.com/paper/2609.34381/) (2026)
- [Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation](https://mlsanity.com/paper/2610.05608/) (2026)

## Abstract (arXiv)

Text-to-video (T2V) diffusion models have recently achieved impressive visual quality, yet most systems still generate silent clips and treat audio as a secondary concern. Existing audio-video generation pipelines typically decompose the task into cascaded stages, which accumulate errors across modalities and are trained under separate objectives. Recent joint audio-video generators alleviate this issue but often rely on dual-tower architectures with ad-hoc cross-modal bridges and static, single-shot text conditioning, making it difficult to both reuse T2V backbones and to reason about how audio, video and language interact over time. To address these challenges, we propose 3MDiT, a unified tri-modal diffusion transformer for text-driven synchronized audio-video generation. Our framework models video, audio and text as jointly evolving streams: an isomorphic audio branch mirrors a T2V backbone, tri-modal omni-blocks perform feature-level fusion across the three modalities, and an optional dynamic text conditioning mechanism updates the text representation as audio and video evidence co-evolve. The design supports two regimes: training from scratch on audio-video data, and orthogonally adapting a pretrained T2V model without modifying its backbone. Experiments show that our approach generates high-quality videos and realistic audio while consistently improving audio-video synchronization and tri-modal alignment across a range of quantitative metrics.