SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 6 days ago • 154
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks Paper • 2608.01964 • Published 6 days ago • 161
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 24 days ago • 211
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable Paper • 2607.13285 • Published 26 days ago • 232
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 19 days ago • 309
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 356
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model Paper • 2603.21986 • Published Mar 23 • 125
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory Paper • 2604.08995 • Published Apr 10 • 51
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published Apr 15 • 127
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation Paper • 2604.19636 • Published Apr 21 • 88
view article Article The First Healthcare Robotics Dataset and Foundational Physical AI Models for Healthcare Robotics nvidia • Mar 16 • 32
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training Paper • 2603.12255 • Published Mar 12 • 91
BitDance: Scaling Autoregressive Generative Models with Binary Tokens Paper • 2602.14041 • Published Mar 13 • 55