LAION-AUDIO-XL & CLAP2 Collection Release of the LAION-Audio-XL dataset and the CLAP2 model achitectures • 7 items • Updated 1 day ago • 2
Speech-to-Speech Training Corpora Collection Full-duplex speech-to-speech pre-, mid- and post-training corpora. Paid early access: [email protected]. In development. • 3 items • Updated 3 days ago • 2
view article Article Mundo: From seeing a place to simulating what happens there Luo-Yihang • 15 days ago • 84
Flora Collection Flora: An Open Model Suite for Scaling Robotics Data Engines • 3 items • Updated 18 days ago • 48
Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy Corrections Paper • 2609.03591 • Published Sep 3 • 1
Muse Spark Open Collection Muse Spark Open model. A 816B parameter model with 42B Active parameters. BF16 and NVFP4 Weights. • 2 items • Updated 23 days ago • 175
Mage Collection A family of lightweight multimodal models, including understanding and generation. • 8 items • Updated Jul 26 • 35
EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ Paper • 2610.18872 • Published 26 days ago • 21
Multics: Generative Multi-Player World Model with Hierarchical Communication Paper • 2610.17201 • Published 27 days ago • 57
MiniCPM-V 4.7 Collection A new chapter in on-device multimodal Al. • 15 items • Updated 23 days ago • 70
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation Paper • 2601.15369 • Published Jan 21 • 23
TermGrade Collection 1k graded terminal environments, 36k trajectories, and the RL run they trained. • 5 items • Updated 30 days ago • 6
TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning Paper • 2610.10288 • Published Oct 7 • 8