Video = World + Event Stream
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%Gepard : 0.6B streaming TTS built for real-time dialogue - 20× realtime factor, ~50ms time-to-first-audio, vLLM-native, Apache 2.0 →
- PossiblePossibly related (embedding) · 49%Best Dictation Software for Windows 2026, Wispr Flow vs Dragon vs Free Open Source Honest Comparison - YouTube →
- FuzzyOverlapping authors or contributors · 62%Zeyi-Lin/HivisionIDPhotos →
“Shared author/contributor keys: lin”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%DietrichGebert/ponytail →
“Shared author/contributor keys: cheng”
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Lianghua Huang →
“Video = World + Event Stream”