Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations Paper • 2510.23607 • Published Oct 27, 2025 • 177
view article Article Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders Jul 9, 2025 • 748
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models Paper • 2505.10554 • Published May 15, 2025 • 120
Kimina Prover Preview Collection State-of-the-Art Models for Formal Mathematical Reasoning • 5 items • Updated Apr 28, 2025 • 33
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper • 2503.03601 • Published Mar 5, 2025 • 232
SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models Paper • 2503.07605 • Published Mar 10, 2025 • 66
❄️January 2025 - Open releases from the Chinese community Collection 33 items • Updated Nov 20, 2025 • 13
Cosmos Collection ⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos-predict25 • 31 items • Updated 11 days ago • 299
Medical SAM 2: Segment medical images as video via Segment Anything Model 2 Paper • 2408.00874 • Published Aug 1, 2024 • 52
view article Article Docmatix - a huge dataset for Document Visual Question Answering Jul 18, 2024 • 77
MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers Paper • 2406.10163 • Published Jun 14, 2024 • 33
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks Paper • 2311.06242 • Published Nov 10, 2023 • 95