# Video = World + Event Stream

arXiv: https://arxiv.org/abs/2607.15038 · HTML: https://mlsanity.com/paper/2607.15038/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling](https://mlsanity.com/paper/2512.14614/) (2025)
- [Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory](https://mlsanity.com/paper/2604.08995/) (2026)
- [StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars](https://mlsanity.com/paper/2512.22065/) (2025)
- [RealWonder: Real-Time Physical Action-Conditioned Video Generation](https://mlsanity.com/paper/2603.05449/) (2026)
- [Body of Her: A Preliminary Study on End-to-End Humanoid Agent](https://mlsanity.com/paper/2408.02879/) (2024)
- [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)
- [FlowAct-R1: Towards Interactive Humanoid Video Generation](https://mlsanity.com/paper/2601.10103/) (2026)
- [Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models](https://mlsanity.com/paper/2606.25041/) (2026)
- [Wan-Streamer v0.2: Higher Resolution, Same Latency](https://mlsanity.com/paper/2607.04443/) (2026)

## Built on by (most cited first, 2 of 2)

- [EchoWM: Open and Enterable Omnimodal World Models](https://mlsanity.com/paper/2608.23189/) (2026)
- [Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention](https://mlsanity.com/paper/2607.20940/) (2026)

## Abstract (arXiv)

We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persistent context in which a video unfolds, including the environment, scene, subjects, ambient acoustic conditions, voice characteristics, and other relatively stable conditions. The event stream is everything that changes over time within that world, including scene or environmental changes, subject behavior, speech, and other sounds. This yields a general-purpose pretraining task over large amounts of real video: given a world and incoming input, predict how the world moves, changes, and responds in real time. The resulting competence can be specialized to a broad family of real-time downstream tasks. We instantiate it on real-time full-duplex audio-visual interaction, where the event stream is the agent's speech together with free-form behavior. Functionally, the model's multimodal understanding process is vision-language-action-like: it maps multimodal user input to language-form speech and behavior actions. Wan-Streamer v0.3 preserves the v0.2 operating point: 640x368 video at 25 FPS, a 160 ms streaming unit, approximately 200 ms model-side response latency, and approximately 550 ms total interaction latency under a 350 ms bidirectional network budget.