Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning Paper β’ 2510.19338 β’ Published 14 days ago β’ 110
Kimi Linear: An Expressive, Efficient Attention Architecture Paper β’ 2510.26692 β’ Published 5 days ago β’ 87
Kimi-Linear-A3B Collection Moonshot's experimental MoE model with Kimi Delta Attention β’ 3 items β’ Updated 4 days ago β’ 9
view article Article huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning 9 days ago β’ 53
Emu3.5 Collection Native Multimodal Models are World Learners π β’ 3 items β’ Updated 5 days ago β’ 62
Emu3.5: Native Multimodal Models are World Learners Paper β’ 2510.26583 β’ Published 5 days ago β’ 94
view article Article 3+ Years of ML & Society at Hugging Face π€π€π§βπ€βπ§ By yjernite and 3 others β’ 6 days ago β’ 13
view article Article On the Shifting Global Compute Landscape By huggingface and 1 other β’ 6 days ago β’ 40
Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers Paper β’ 2510.11370 β’ Published 22 days ago β’ 2
Glyph: Scaling Context Windows via Visual-Text Compression Paper β’ 2510.17800 β’ Published 15 days ago β’ 64
π October 2025 - China Open Source Highlights Collection 27 items β’ Updated about 9 hours ago β’ 4
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level Paper β’ 2411.03562 β’ Published Nov 5, 2024 β’ 68