Duo: A Reciprocal World Model for Full-Duplex Interaction
cs.CV, cs.SD
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/inclusionAI/Duo
Project page: https://duo-v1.github.io
Terminology
Sources
- Qwen3-VL Technical Report
- Genie: Generative Interactive Environments
- Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
- Hy-Nomas: Towards Free-form Interactive World Generation
- LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
- Moshi: a speech-text foundation model for real-time dialogue
- Infinite Worlds with Versatile Interactions
- World Models
- LTX-2: Efficient Joint Audio-Visual Foundation Model
- GAIA-1: A Generative World Model for Autonomous Driving
- Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
- Flow Matching for Generative Modeling
- Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
- Cosmos World Foundation Model Platform for Physical AI
- Advancing Open-source World Models
- Qwen3-ASR Technical Report
- MOVA: Towards Scalable and Synchronized Video-Audio Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs