# Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory

arXiv: https://arxiv.org/abs/2607.26818 · HTML: https://mlsanity.com/paper/2607.26818/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 30 of 33)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)
- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [HunyuanVideo 1.5 Technical Report](https://mlsanity.com/paper/2511.18870/) (2025)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://mlsanity.com/paper/2303.14717/) (2023)
- [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)
- [OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation](https://mlsanity.com/paper/2412.00115/) (2024)
- [Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation](https://mlsanity.com/paper/2309.16429/) (2023)
- [UniVerse-1: Unified Audio-Video Generation via Stitching of Experts](https://mlsanity.com/paper/2509.06155/) (2025)
- [MOVA: Towards Scalable and Synchronized Video-Audio Generation](https://mlsanity.com/paper/2602.08794/) (2026)

## Built on by (most cited first, 1 of 1)

- [WorldSonus: Bringing Sound to Worlds](https://mlsanity.com/paper/2610.08760/) (2026)

## Abstract (arXiv)

Audio-video generative models achieve impressive quality but suffer from high latency, making them unsuitable for real-time applications. Although several streaming audio-video generation methods have been proposed, they remain costly and fail to support long-form generation. To address this, we propose Ripple, a real-time joint audio-video generation system with a cross-modal recurrent memory mechanism. To enable efficient streaming inference while preserving long-term context, Ripple combines a fixed-length sliding-window attention with modality-specific memory states that continuously summarize audio and video context. Cross-modal memory interaction is further introduced to enhance audio-visual synchronization. To learn this memory-augmented model effectively, we devise a three-stage training recipe: (1) adapting a bidirectional audio-video teacher to block-wise causal attention with simulated memory, (2) optimizing the memory construction and interaction pipeline through end-to-end distillation, and (3) applying online reinforcement post-training tailored for streaming audio-video generation. As a result, Ripple achieves ~28 FPS at 480P resolution, over faster than the teacher, while capable of coherent long-form generation. Extensive experiments on both short-video and long-video benchmarks demonstrate our superior performance over existing offline and online joint audio-video generation methods.