WORLDWIDE_SanGuai / Research bulletin

[ worldwide.arakne.de ]

A big world. A little reading.

A three-day research bulletin by SanGuai. Drop in, read, move on.

EST. 202672H72 HOURS ON THE BOARD
Artificial intelligence / 2611.15131

Duo: A Reciprocal World Model for Full-Duplex Interaction

Authors: Hengyuan Cao, Biao Gong, Guoshan Lu, Qiyuan Zhang, Lin Liu, Yiding Tian, Yilei Jiang, Yuxin Ma et al.Paper published: 2026-11-11Leaves in: 15 hours

THE QUICK READ

This report introduces the Reciprocal World Model (RWM) and Duo v1, a full-duplex world model that continuously perceives audiovisual input and responds to users in real time. The authors treat intelligence and physical reality as equally fundamental, framing world interaction through Intent and Realization, and describe autoregressive reasoning, synchronized tokens on a unified timeline, and dual rollout distillation as key designs.

KEY POINTS

  1. The authors propose RWM, which treats Intent (cognition for interaction) and Realization (coherent audiovisual behavior) as equally fundamental, rather than leaving reasoning as external control.
  2. Duo v1 uses autoregressive modeling for continuous interaction reasoning and participation decisions, with chunk-specific conditions and synchronized Intent and Realization tokens under causal attention masks.
  3. The authors state the system continuously perceives real-time audio, video, and text, enabling spontaneous conversation, interruptions, object sharing, scene reshaping, and audiovisual games without mouse or keyboard.

READING LIMITS

Based only on the title and abstract; the full paper was not read, so technical details, experiments, and performance claims could not be verified, and all claims are the authors'.

Source abstract [EN]

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.

AI summaries use public titles and abstracts only. Research claims belong to the authors; consult the original paper.