Hugging Face Blog
778 posts indexed since 2026
Monthly Post Volume
Monthly post counts
| Month | Posts |
|---|---|
| 1-2026 | 56 |
| 2-2026 | 56 |
| 3-2026 | 63 |
| 4-2026 | 61 |
| 5-2026 | 56 |
| 6-2026 | 94 |
| 7-2026 | 74 |
| 8-2026 | 75 |
| 9-2026 | 84 |
| 10-2026 | 99 |
| 11-2026 | 60 |
Post Details
778 matching posts
| Title | Author | Published | Words | HN Pts |
|---|---|---|---|---|
| Hugging Face ❤️ TorchTPU: TPUs, Natively | Alvaro Moran, Jingya Huang, Simon Pagezy, Jeff Boudier, and Régis Pierrard | 2026-10-20 | 1,241 | -- |
| NVIDIA Cosmos3-H-Dreams: Bringing Clinical Surgery to Life Through Generative Simulation | Lukas Zbinden, Javier Gamazo, Nigel Nelson, Mostafa Toloui, and Sean Huver | 2026-10-20 | 1,304 | -- |
| A curriculum for post-training agents | ben burtenshaw, Sergio Paniego, and merve | 2026-10-20 | 1,090 | -- |
| AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms | Mattt | 2026-10-20 | 897 | -- |
| Do we really need bigger AI weather forecasting models to improve resolution? | Emma Scharfmann, Aritra Roy Gosthipaty, and Kashif Rasul | 2026-10-20 | 3,925 | -- |
| MPS in PyTorch 2.15 | Irakli Salia and Khushi Agrawal | 2026-10-20 | 2,314 | -- |
| TorchNeuron: running HF models on AWS Trainium is easier than ever | Régis Pierrard, Simon Pagezy, Michael Benayoun, Jingya Huang, Alvaro Moran, David Corvoysier, and Jeff Boudier | 2026-10-19 | 1,677 | -- |
| SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers | Paulo Moura and Raphael Sourty | 2026-10-19 | 7,063 | -- |
| Sort your prompts: a free speed-up for MoE batch inference | Abdennacer Badaoui | 2026-10-19 | 1,722 | -- |
| Estimating physics from images: what real measurements reveal | Luca Cilio | 2026-10-16 | 1,748 | -- |
| Welcome Beam: a 501B open model you can own, customize, and scale | ben burtenshaw, merve, and Pedro Cuenca | 2026-10-16 | 4,373 | -- |
| Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline | Will Jennings, Kiran Praveen, Sriharsha Niverty, Raviraj Joshi, Markus Kliegl, Yev Meyer, Utkarsh Vaidya, and Niket Agarwal | 2026-10-16 | 2,419 | -- |
| The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function | Yihua Zhang | 2026-10-15 | 12,444 | -- |
| Extending Nemotron 3.5 Super 120B VL with Agentic Web Development Capabilities | Henrik Klagges, Thomas Endres, Robert Dahlke, Fabian Klemm, Andreas Rabenstein, and Lars Reimann | 2026-10-15 | 2,184 | -- |
| Welcome FLUX.3 Image Klein in Diffusers: The latest open image generation model from Black Forest Labs | Aritra Roy Gosthipaty, Sayak Paul, and Linoy Tsaban | 2026-10-15 | 3,468 | -- |
| Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint | Kate Soule, Subhajit Chaudhury, Hendrik Strobelt, and Luis A Lastras | 2026-10-15 | 818 | -- |
| The Missing Piece in LLM Memory: Why Long Context and Retrieval Aren't Enough for Belief Revision | Rahul Vimalkanth and Tanish Chudiwal | 2026-10-15 | 12,061 | -- |
| Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta | Pedro Cuenca, merve, ben burtenshaw, Guarin Flück, Quentin Gallouédec, Alvaro Bartolome, Serveurperso, and Jun Kim | 2026-10-15 | 4,375 | -- |
| Apertus 1.5 Release Notes | Hanna Yukhymenko, Oleg Lavrovsky, and Y Metz | 2026-10-15 | 2,735 | -- |
| Tokenmaxxing BERT: 50x faster tokenization | Simon Brandeis | 2026-10-15 | 3,127 | -- |
| QVAC TranscribePsy: State-of-the-Art On-Device Multilingual Speech Recognition | Tianchi Liu, Mohammadreza Zolfaghari, Nicholas Moratelli, Khurram Azeem Hashmi, Rishabh Jain, pengfei, Louis, Changdae Park, Mathias Buus, and Amril Nurman | 2026-10-14 | 3,117 | -- |
| HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost | Kyle Wiggers | 2026-10-14 | 856 | -- |
| Introducing Lumma-Fev-27B | Abhay kumar, Vishesh Tripathi, Ramsha, and Rohit | 2026-10-14 | 1,063 | -- |
| When agents self-improve, what should persist? | Val Alexander | 2026-10-14 | 1,902 | -- |
| UltraBERT: One Encoder for Classification and Retrieval | Data Mining and Information Systems Lab, Jungwoo Park, and Taewhoo Lee | 2026-10-14 | 2,949 | -- |
| Backpropagation on an Inference-Only NPU: Pretraining VKORE-46M-NPU From Scratch | VIDRAFT_LAB | 2026-10-14 | 1,255 | -- |
| One Decision Model Instead of a Ranking Team: Short-Video and News Recommendation with autotrust/JEV-27B-VL | Hai Yu and Josh Liu | 2026-10-13 | 1,604 | -- |
| Introducing Llama Windows: llama.cpp in your Windows tray | Morgan Funtowicz, Jeff Boudier, and Emanuil Rusev | 2026-10-13 | 944 | -- |
| Fine-Tune ASR for Your Domain with NVIDIA Speech Agent Skills | Francesco, Myungjong Kim, Jinhan Wang, Yitagessu Gebremedhin, Adi- margolin, and Maryam Motamedi | 2026-10-13 | 2,823 | -- |
| Run fast, private agents on-device with LFM2.5-24B-A2B | Raahul Vignesh, Song Duong, Akhilesh Deepak Gotmare, Fernando Fernandes Neto, Jiahui Wang, Mayank Agarwal, nathan ranchin, Sergei Tilga, Sinoué GAD, Tim Seyde, Zetian Li, changyi yang, Simon Lee, Leonie Monigatti, Maxime Labonne, Karthik Macherla, Alfred | 2026-10-13 | 1,226 | -- |
| Sparseup-fr: A French replication of Linkup's sparse embedding model | Loïck BOURDOIS | 2026-10-12 | 1,852 | -- |
| ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third | Maxence Lasbordes, Raphael Sourty, Aarush, and Amélie Chatelain | 2026-10-12 | 4,630 | -- |
| Basis Global Emotions: 525 hours of expressive speech across 108 locales | Alexis Sursock | 2026-10-12 | 858 | -- |
| UIBK-Embedding-v1: A Dense and a Late-Interaction Retriever in One Model, One Index and One Search | Abdelrahman Abdallah | 2026-10-12 | 6,061 | -- |
| The Open Quantum Challenge: Quantum Simulation and QEC Decoding on Classical GPUs | VIDRAFT_LAB | 2026-10-11 | 667 | -- |
| Leading the System One Mosaic Benchmark: What Darwin-27B-ZTC-v2's #1 Means | VIDRAFT_LAB | 2026-10-09 | 1,044 | -- |
| Impactful scheduling for GPU clusters | Kyle Wiggers | 2026-10-09 | 3,389 | -- |
| Six Questions to Ask a LeRobot Dataset Before You Train | Harpreet Sahota | 2026-10-08 | 4,316 | -- |
| Carbon-A: Finding genes in known and unknown genomes | Georgia Channing, Leandro von Werra, and Gener Team | 2026-10-08 | 1,612 | -- |
| LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model | Said Taghadouini, Adrien Cavaillès, and Baptiste Aubertin | 2026-10-08 | 3,917 | -- |
| The model that didn't exist, so you made it yourself | yuvraj sharma and Abubakar Abid | 2026-10-08 | 1,965 | -- |
| Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration | VIDRAFT_LAB | 2026-10-08 | 1,279 | -- |
| Introducing Falcon ASR | Abdul Muneer, Rishabh Saraf, Ramesh Gundluru, Shamsa Hamad, Lepauloux, and Hakim Hacid | 2026-10-07 | 1,391 | -- |
| One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO | Aleksander, Igor Gitman, Sean Narenthiran, Mehrzad Samadi, and Somshubra Majumdar | 2026-10-07 | 1,122 | -- |
| Multimodal open d1 decision models for the edge | Aurelien Lac, Fernando Fernandes Neto, Edoardo Mosca, Maxime Labonne, and Leonie Monigatti | 2026-10-07 | 1,144 | -- |
| ViDiHand: The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction | WANGYUXI, JCK, Yufei Liu, and Xingang Pan | 2026-10-06 | 1,792 | -- |
| Falcon OCR Arabic: 270M Parameters State-of-the-Art Arabic OCR | Falcon LLM TII UAE | 2026-10-06 | 1,531 | -- |
| Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance | Shaikha Alsuwaidi, Omar saif alkaabi, Maitha Alhammadi, Ahmed Alzubaidi, Mohammed Alyafeai, Leen AlQadi, Basma Boussaha, and Hakim Hacid | 2026-10-06 | 2,674 | -- |
| FiftyOne Now Reads LeRobot: 50 Embodiments, 497 Episodes, One Indexed Dataset | Harpreet Sahota | 2026-10-05 | 4,827 | -- |
| Universal Modder: A Practical Guide to AI Game Modding | zhangcheng | 2026-10-04 | 1,290 | -- |