Duo-v1 Collection Duo is a modular Reciprocal World Model for full-duplex interaction. • 4 items • Updated 7 days ago • 15
UniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation Paper • 2611.16517 • Published 8 days ago • 14
Duo: A Reciprocal World Model for Full-Duplex Interaction Paper • 2611.15131 • Published 9 days ago • 48
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 25 days ago • 52
Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation Paper • 2610.30926 • Published 29 days ago • 25
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory Paper • 2610.19366 • Published Oct 14 • 51
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published Sep 3 • 59
Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence Paper • 2607.12477 • Published Jul 14 • 7
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published Aug 3 • 67
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published Jul 16 • 104
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published Jul 13 • 57
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning Paper • 2606.26790 • Published Jun 25 • 59
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating Paper • 2606.21661 • Published Jun 19 • 22
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation Paper • 2606.26058 • Published Jun 24 • 66
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models Paper • 2606.25041 • Published Jun 23 • 123