Papers
arxiv:2606.09186

DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction

Published on Jun 8
Authors:
,
,
,
,
,
,
,
,
,

Abstract

DuplexOmni enables real-time multimodal full-duplex interaction by separating model capabilities into asynchronous interaction and thinking layers, with the former processing streaming inputs and generating responses while the latter provides complex reasoning and tool use.

Human interaction is continuous, multimodal, and full-duplex by nature. Although recent omni models have made substantial progress in unified speech, vision, and text modeling, combining seamless real-time interaction with complex reasoning and tool use remains challenging. We present DuplexOmni, a method for real-time multimodal full-duplex interaction. DuplexOmni separates model capability into an interaction layer and a thinking layer, which collaborate asynchronously in parallel. The interaction layer is implemented by the DuplexOmni model, an end-to-end system that processes streaming audio and video inputs while generating text and speech responses in real time. The thinking layer is a pluggable module that provides complex reasoning and tool-use capabilities. To support this method, we further develop a Writer-Director pipeline for constructing continuous-interaction training data. Experiments show that DuplexOmni achieves strong performance on multiple public benchmarks and exhibits natural full-duplex interaction ability.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.09186
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.09186 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.09186 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.