# Wan-Streamer v0.2: Higher Resolution, Same Latency

arXiv: https://arxiv.org/abs/2607.04443 · HTML: https://mlsanity.com/paper/2607.04443/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time](https://mlsanity.com/paper/2404.10667/) (2024)
- [MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction](https://mlsanity.com/paper/2604.27393/) (2026)
- [StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars](https://mlsanity.com/paper/2512.22065/) (2025)
- [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)
- [From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models](https://mlsanity.com/paper/2509.14515/) (2025)
- [Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models](https://mlsanity.com/paper/2606.25041/) (2026)
- [MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation](https://mlsanity.com/paper/2512.03034/) (2025)

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

- [Video = World + Event Stream](https://mlsanity.com/paper/2607.15038/) (2026)
- [Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming](https://mlsanity.com/paper/2608.05663/) (2026)

## Abstract (arXiv)

We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises the interactive output stream from 192x336 to 640x368 while preserving approximately 200 ms model-side signal-to-signal latency at 25 FPS. The higher-resolution stream supports scene-grounded mid-shot agents whose posture, gaze, hands, nearby objects, and local scene layout remain legible during real-time conversation. To support the larger visual stream without adding user-visible delay, v0.2 keeps the thinker as a single-GPU low-latency path for streaming perception, the short language/state Transformer pass that builds the generation cache, and final decoding. The performer becomes a multi-GPU Ulysses-style context-parallel group for the expensive next-unit latent generation. Each performer rank writes incoming K/V into a pre-sharded local cache. The long high-resolution latent video sequence is split across ranks for denoising and gathered through Ulysses communication, while the much shorter audio latent sequence is generated without sequence sharding. In this split, the thinker's language/state computation reaches the performer only as K/V conditioning, so no separate language sequence has to be communicated inside the performer group. This concentrates additional hardware on visual generation while preserving the compact thinker-performer boundary, keeping total remote interaction latency at approximately 550 ms when a 350 ms bidirectional network budget is included.