inclusionAI (Hengyuan Cao, Biao Gong, Guoshan Lu, Qiyuan Zhang, Lin Liu, Yiding Tian, Yilei Jiang, Yuxin Ma) · Full-Duplex World Model
Duo: A Reciprocal World Model for Full-Duplex Interaction
The paper introduces the Reciprocal World Model (RWM) and Duo v1, a full-duplex model that continuously takes in real-time audio, video and text while responding to users. It pairs autoregressive interaction reasoning (Intent) with audiovisual generation (Realization) on a shared timeline, using causal attention masks and dual rollout distillation to reduce distribution shift. The page gives no benchmark figures or licence details, and says a next version is coming.
Open the source ↗Similar Audio & Speech releases
- Sophon-Realtime v1
Adventists AI · Full-Duplex Voice · Week 47, 2026
- Live 3
Fish Audio · Full-Duplex Voice · Week 47, 2026
- Muse Realtime Voice and Muse Realtime Avatar
Meta · Realtime voice avatars · Week 46, 2026
- MOSS-Live
模思智能 (MOSS) · Full-duplex voice agent · Week 46, 2026
- Dessa
Block (Dessa research lab) · Speech-only conversation model · Week 45, 2026
- Eleven v4 and v4 Turbo
ElevenLabs · Expressive TTS Model · Week 41, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.