Video World Models · 2026-11-13

Duo: A Reciprocal World Model for Full-Duplex Interaction

Hengyuan Cao, Biao Gong, Guoshan Lu, Qiyuan Zhang, Lin Liu, Yiding Tian, Yilei Jiang, Yuxin Ma, Chengzhang Wu, Kun Chen, Yiqian Xie, Ting Liu, Xin Zheng, Xijun Gu, Tianren Ma, Jiancheng Pan, Chi Zhang, Xuzhe Zheng, Siyi Li, Zhenzhong Lan

arXiv:2611.15131PDFCode

AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.

TL;DR

The authors introduce the Reciprocal World Model (RWM) and Duo v1, a full-duplex world model that continuously perceives real-time audio, video, and text while responding in real time. Duo v1 uses a chunk-wise setup with an Autoregressive Intent Module for participation decisions and a causal audiovisual Realization Module that generates audio/video latents conditioned on intent, synchronized on a unified timeline. They train in stages and distill for live interaction.

Why it matters

Most world models simulate the physical side while leaving reasoning/decision-making external. The authors propose RWM where intelligence (Intent) and realization (coherent audiovisual behavior) are both intrinsic, enabling real-time reciprocal interaction. Duo v1 provides a concrete chunk-wise architecture and training/distillation strategy for full-duplex audiovisual participation with causal constraints.

Method

  • Reciprocal chunk-wise full-duplex interaction: an Intent Module outputs either <speak>+text or <wait>, and a Realization Module generates audio/video latents conditioned on intent hidden states plus synchronized user inputs and prior assistant history.
  • Causal synchronization on a unified timeline: module-specific attention masks enforce causality within and across chunks; the realization module restricts attention so generated media in a chunk cannot access future inputs.
  • Mitigating distribution shift via dual rollout distillation: during distillation, a frozen Intent Module autoregressively generates the final assistant turn, and the Realization Module conditions on those intent features and its own generated audiovisual history.

Limitation

The authors state that Duo v1 is preliminary and currently supports basic audiovisual conversation; response timing, consistency over longer sessions, and recovery from misunderstandings require broader evaluation.

Abstract (from arXiv)

In this report, we introduce the Reciprocal World Model (RWM) and present Duo v1, a full-duplex world model that continuously perceives audiovisual inputs while responding to users in real time. The RWM treats intelligence and physical reality as equally fundamental to what constitutes a world. Existing world models largely focus on simulating the latter, leaving reasoning and decision-making as external controls rather than intrinsic parts of the world itself. In RWM, we identify two equally fundamental capabilities: Intent, which provides the cognition underlying world interactions, and Realization, which generates coherent audio-visual behavior. To realize this formulation, Duo v1 introduces three key technical designs: (1) Leveraging autoregressive modeling for continuous interaction reasoning and participation decisions, rather than restricting it to instruction understanding for diffusion models. (2) Constructing chunk-specific conditions and synchronize tokens across Intent and Realization on a unified timeline. Module-specific attention masks enforce causal dependencies both within and across chunks, preventing access to future inputs. (3) Mitigating distribution shift in both modules through dual rollout distillation, training on autoregressively generated Intent tokens and synthesized audiovisual histories from Realization. Both modules continuously perceive real-time audio, video, and text, enabling full-duplex interaction with spontaneous conversations and interruptions. Beyond conversation, users can share real objects, reshape virtual scenes, guide assistants, or play audiovisual games without mouse or keyboard controls. The release of Duo v1 makes our first step, with the next version coming soon. We look forward to broader exploration of this emerging field.

Related papers

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First announced by arXiv: 2026-11-13 · Indexed by Pub-AI: 2026-11-13 UTC

preprint

Duo: A Reciprocal World Model for Full-Duplex Interaction

Hengyuan Cao, Biao Gong, Guoshan Lu, Qiyuan Zhang, Lin Liu, Yiding Tian, Yilei Jiang, Yuxin Ma, Chengzhang Wu, Kun Chen, Yiqian Xie, Ting Liu, Xin Zheng, Xijun Gu, Tianren Ma, Jiancheng Pan, Chi Zhang, Xuzhe Zheng, Siyi Li, Zhenzhong Lan

First announced by arXiv: 2026-11-13 · Original record ↗

arxiv
2611.15131
Explicit source versions (1)
  • v1 · Date not supplied
  1. Preprint available

    Source date: 2026-11-13 · First detected: 2026-11-13 UTC · Historical baseline

    Source evidence (1)
    • Official evidence ↗ · RSS guid=oai:arXiv.org:2611.15131v1; arxiv:announce_type=new; item pubDate (official metadata)
Abstract · arxiv

In this report, we introduce the Reciprocal World Model (RWM) and present Duo v1, a full-duplex world model that continuously perceives audiovisual inputs while responding to users in real time. The RWM treats intelligence and physical reality as equally fundamental to what constitutes a world. Existing world models largely focus on simulating the latter, leaving reasoning and decision-making as external controls rather than intrinsic parts of the world itself. In RWM, we identify two equally fundamental capabilities: Intent, which provides the cognition underlying world interactions, and Realization, which generates coherent audio-visual behavior. To realize this formulation, Duo v1 introduces three key technical designs: (1) Leveraging autoregressive modeling for continuous interaction reasoning and participation decisions, rather than restricting it to instruction understanding for diffusion models. (2) Constructing chunk-specific conditions and synchronize tokens across Intent and Realization on a unified timeline. Module-specific attention masks enforce causal dependencies both within and across chunks, preventing access to future inputs. (3) Mitigating distribution shift in both modules through dual rollout distillation, training on autoregressively generated Intent tokens and synthesized audiovisual histories from Realization. Both modules continuously perceive real-time audio, video, and text, enabling full-duplex interaction with spontaneous conversations and interruptions. Beyond conversation, users can share real objects, reshape virtual scenes, guide assistants, or play audiovisual games without mouse or keyboard controls. The release of Duo v1 makes our first step, with the next version coming soon. We look forward to broader exploration of this emerging field.