PixVerse R2 scales real-time omni world models with Omni Causal AR and multimodal control
future_coded · x · 2026-09-25
PixVerse released the technical report for R2, its real-time omni audiovisual world model.
- Core framework: Omni Causal AR scales the streaming-video foundation across data, modalities, tasks, control signals, and temporal horizons, while Real-Time Acceleration brings these capabilities into ultra-few-step real-time operation without relearning.
- Unified multimodal interface: text, references, audio, actions, and agent-generated controls all update the same persistent running world state.
- Positioning: builds on R1, the first publicly launched general-purpose real-time audiovisual world model — "the engine is the model," where next frames and sounds come from prior state plus player input rather than baked maps.
- Early uses: game ideation before greybox, camera/shot exploration, story-branch testing; identity consistency has improved but isn't perfect yet.
More from Multimodal
- Ant Group's open-source Ming-3.0-tts-0.5B tops Open TTS Leaderboard with 0.88 WER — NielsRogge · 2026-11-12
- Llama app adds simultaneous voice, image and video input, running locally on LFM3-Omni — mervenoyann · 2026-11-12
- Seedance 2.5 can now generate 4K video directly, no upscaling needed — charis_ai · 2026-11-12
- codec.audio benchmarks neural audio codecs on noisy in-the-wild speech; MOSS tops — kastnerkyle · 2026-11-11
- State of AI video: Isaiah Ross's hyper-realistic showcase hailed as current peak — LinusEkenstam · 2026-11-11
- State of AI video: generative clips reach startling new realism — LinusEkenstam · 2026-11-11