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

Source: https://huggingface.co/papers/2607.04443 Published on Jul 5

#1 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Wan-Streamer v0.2 enhances audio-visual interaction by increasing visual resolution while maintaining low latency through optimized thinker-performer architecture with multi-GPU parallel processing.

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 forstreaming perception, the short language/stateTransformerpass that builds thegeneration cache, andfinal decoding. The performer becomes a multi-GPUUlysses-style context-parallel groupfor the expensive next-unit latent generation. Each performer rank writes incoming K/V into apre-sharded local cache. The long high-resolution latent video sequence is split across ranks fordenoisingand gathered throughUlysses communication, while the much shorteraudio latent sequenceis generated without sequence sharding. In this split, the thinker’slanguage/state computationreaches the performer only asK/V conditioning, so no separate language sequence has to be communicated inside the performer group. This concentrates additional hardware onvisual generationwhile preserving the compact thinker-performer boundary, keeping total remote interaction latency at approximately 550 ms when a 350 ms bidirectional network budget is included.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.04443

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.04443 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.04443 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.04443 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.