# OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

arXiv: https://arxiv.org/abs/2603.11647 · HTML: https://mlsanity.com/paper/2603.11647/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 50 of its 54 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Placed in

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

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (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)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation](https://mlsanity.com/paper/2212.09478/) (2022)

## Built on by (most cited first, 16 of 16)

- [Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation](https://mlsanity.com/paper/2604.23632/) (2026)
- [EchoWM: Open and Enterable Omnimodal World Models](https://mlsanity.com/paper/2608.23189/) (2026)
- [Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation](https://mlsanity.com/paper/2604.10098/) (2026)
- [Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models](https://mlsanity.com/paper/2606.25041/) (2026)
- [MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model](https://mlsanity.com/paper/2606.17800/) (2026)
- [A Systematic Post-Train Framework for Video Generation](https://mlsanity.com/paper/2604.25427/) (2026)
- [Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds](https://mlsanity.com/paper/2608.23383/) (2026)
- [RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control](https://mlsanity.com/paper/2605.06051/) (2026)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation](https://mlsanity.com/paper/2609.36995/) (2026)
- [Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory](https://mlsanity.com/paper/2607.26818/) (2026)
- [OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars](https://mlsanity.com/paper/2607.23023/) (2026)
- [Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming](https://mlsanity.com/paper/2608.05663/) (2026)
- [UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos](https://mlsanity.com/paper/2608.11752/) (2026)
- [All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation](https://mlsanity.com/paper/2609.27901/) (2026)
- [Generative World Simulation with DAO and JING](https://mlsanity.com/paper/2610.19726/) (2026)

## Abstract (arXiv)

Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework to distill an offline, dual-stream bidirectional diffusion model into a high-fidelity streaming autoregressive generator. However, naively applying causal distillation to such dual-stream architectures triggers severe training instability, due to the extreme temporal asymmetry between modalities and the resulting token sparsity. We address the inherent information density gap by introducing an Asymmetric Block-Causal Alignment with a zero-truncation Global Prefix that prevents multi-modal synchronization drift. The gradient explosion caused by extreme audio token sparsity during the causal shift is further resolved through an Audio Sink Token mechanism equipped with an Identity RoPE constraint. Finally, a Joint Self-Forcing Distillation paradigm enables the model to dynamically self-correct cumulative cross-modal errors from exposure bias during long rollouts. Empowered by a modality-independent rolling KV-cache inference scheme, OmniForcing achieves state-of-the-art streaming generation at ~25 FPS on a single GPU, maintaining multi-modal synchronization and visual quality on par with the bidirectional teacher.Project Page: hrefhttps://omniforcing.comhttps://omniforcing.com