CASA Collection CASA: Cross-Attention as Self-Attention for Efficient Vision-Language Fusion on long context streaming inputs • 6 items • Updated 16 days ago • 6
CommonForms: A Large, Diverse Dataset for Form Field Detection Paper • 2509.16506 • Published Sep 20, 2025 • 19
Less is More: Recursive Reasoning with Tiny Networks Paper • 2510.04871 • Published Oct 6, 2025 • 501
view article Article Welcome EmbeddingGemma, Google's new efficient embedding model +4 Sep 4, 2025 • 267
NeuralOS: Towards Simulating Operating Systems via Neural Generative Models Paper • 2507.08800 • Published Jul 11, 2025 • 80
view article Article Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders Jul 9, 2025 • 757
Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition Paper • 2506.17201 • Published Jun 20, 2025 • 57
Seedance 1.0: Exploring the Boundaries of Video Generation Models Paper • 2506.09113 • Published Jun 10, 2025 • 105
D-FINE Collection State-of-the-art real-time object detection model with Apache 2.0 licence • 15 items • Updated May 5, 2025 • 56
Unsloth Dynamic 2.0 Quants Collection New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 67 items • Updated 9 days ago • 296
Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10, 2025 • 212
olmOCR Collection olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 12 items • Updated 16 days ago • 141