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 |
|---|---|---|---|---|
| Do LLM Routers Actually Route? Quick answer: Not much! | Peter Kruger | 2026-10-26 | 2,535 | -- |
| Reverse Engineering Anything using small open models | Younes B, Nathan Habib, and Lysandre | 2026-10-26 | 2,101 | -- |
| What's new in the hf CLI and huggingface_hub library | Célina Hanouti and Lucain Pouget | 2026-10-26 | 1,149 | -- |
| DecisionFormer | Vishesh Tripathi, Abhay kumar, Rohit, and Ramsha | 2026-10-26 | 4,262 | -- |
| Pretraining a 325M Language Model from Zero on an Inference-Only NPU | VIDRAFT_LAB | 2026-10-26 | 1,570 | -- |
| Build specialized multimodal models with LFM3 | Leonie Monigatti, Jimmy T.H. Smith, Anthony Maltsev, Maxime Labonne, Brandon, Samuel Stevens, Ryan Shubert, Tianshu Yu, Sina, Tim Seyde, Rouzbeh Amin Tafreshi, Alexander Amini, Saniya Karwa, Marc Harkonen, Anna Piunova, Calder Katyal, Ishwarya Ananthabhot | 2026-10-27 | 3,086 | -- |
| Can we trust LLMs to judge whether a research idea is novel? | Kyle Wiggers | 2026-10-27 | 1,767 | -- |
| NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt | Maryam Motamedi, Piotr Żelasko, Kunal Dhawan, Nikolay Karpov, Nune Tadevosyan, Meline Mkrtchyan, Nithin Rao Koluguri, and Francesco | 2026-10-28 | 2,594 | -- |
| A Low-Cost Decision Model on CPU: Optimizing DiffusionGemma with vLLM - Part I | Mia Ojeda | 2026-10-29 | 5,139 | -- |
| Introducing Lumma-Fev-v2 | Rohit, Vishesh Tripathi, Abhay kumar, and Ramsha | 2026-10-29 | 1,834 | -- |
| Announcing Project ProtoStar: Making Publicly Funded Science AI-Ready | Avijit Ghosh, Sayeed Choudhury, Greg Tananbaum, Emma Scharfmann, Georgia Channing, Eunice Mercado-Lara, and Irene Solaiman | 2026-10-29 | 1,610 | -- |
| Granite Switch 4.1.1 — Update models like you update software | Kate Soule, Luis A Lastras, Subhajit Chaudhury, and Abraham Daniels | 2026-10-29 | 376 | -- |
| Welcome Le Chonk: Mistral Large 4 on Hugging Face | merve, Alvaro Bartolome, Rémi Ouazan Reboul, Cyril Vallez, Quentin Gallouédec, Enrique Hernández Calabrés, Juan Julián, Xuan-Son Nguyen, Pedro Cuenca, ben burtenshaw, and Aritra Roy Gosthipaty | 2026-10-29 | 2,500 | -- |
| Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms | Mattt | 2026-10-29 | 2,673 | -- |
| Try an LLM Router That Actually Routes ($1 free credit) | Peter Kruger | 2026-10-29 | 2,000 | -- |
| nemotron-halloween | Rick Grandy and Maryam Motamedi | 2026-10-30 | 2,496 | -- |
| How do we get to plug-and-play robots? | Luca Cilio | 2026-10-30 | 2,368 | -- |
| Clover-35B-A3B-Preview: A New Way for Intelligence | DiffuSpace Core Team | 2026-10-30 | 2,554 | -- |
| ViKernel: Why the Kill Switch Must Live Inside the Model | VIDRAFT_LAB | 2026-11-01 | 1,376 | -- |
| Why We Built Design Creativity Bench: Measuring What AI Coding Benchmarks Miss | Mukund Mohan and Sourabh Upreti | 2026-11-02 | 1,227 | -- |
| Bring Your Own Schema: How We Built kniv v7 | Rohit Rai | 2026-11-02 | 4,905 | -- |
| The Sleeper in the Weights: We Planted a Backdoor in an Agent, and Only the Kernel Caught It | VIDRAFT_LAB | 2026-11-02 | 2,031 | -- |
| Sliding window beats linear attention, but only on short answers | Lukas | 2026-11-02 | 3,055 | -- |
| Palette: teaching a small model to build decks in your design language | Praveen Venkateswaran, Anupama Murthi, and Hamid Adebayo | 2026-11-03 | 2,049 | -- |
| CWE-bench v2: More coverage, quality, and transparency | Gonzalo Gonzalez, Ajay Jagannath, Nazneen Rajani, and Nathan Habib | 2026-11-03 | 841 | -- |
| StateBench: Testing how language models track state changes over long documents | Kyle Wiggers | 2026-11-03 | 1,628 | -- |
| MOPD: how frontier labs merge RL experts into one model and how to do it using TRL | Sergio Paniego | 2026-11-03 | 2,417 | -- |
| Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA? | Sami Marreed, Anupama Murthi, Vinod Muthusamy, Ankita Naik, Segev Shlomov, Jayaram Radhakrishnan, Aminat A, Ayhan Sebin, Hamid Adebayo, Erez Bilgory, Asaf Adi, Jim Laredo, and Merve Unuvar | 2026-11-03 | 1,648 | -- |
| CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat | NeutrinoLiu, YueyangPan, Hanhong Zhao, and coco | 2026-11-03 | 4,426 | -- |
| Transformers Model Integration Contracts | Tarek Ziadé | 2026-11-03 | 1,749 | -- |
| Dharma Field Extractor: Any Document In, Structured Fields in JSON Out | Gabriel Pimenta de Freitas Cardoso, Paulo Henrique de Medeiros Araujo, Bruno Duarte, and Francisco de Almeida Rocha Alves | 2026-11-04 | 1,836 | -- |
| Sand3D: 106,094 3D objects in one code substrate for language models | Thibault Neveu | 2026-11-05 | 1,300 | -- |
| LeRobot v0.7.0: From Terabytes to Prompting Robots | Steven Palma, Pepijn Kooijmans, Caroline Pascal, Khalil Meftah, Maxime Ellerbach, HaomingSong, Nikodem Bartnik, Pablo Montalvo, Martino Russi, Etienne Chassaing, Nicolas Rabault, and Lysandre | 2026-11-05 | 3,303 | -- |
| New NVIDIA Cosmos 3 Open Models for Interactive World Simulation | Pranjali Joshi, Rick Z, Yao Xu, Qianli Ma, Chen-Hsuan Lin, Ming-Yu Liu, Xiang Li, Zhengfei Kuang, Zhonghao Wang, and Jiaxiang Tang | 2026-11-05 | 1,478 | -- |
| A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks. | Olesia Krizhevich, Laurent Mazare, Eric Bezzam, and Eustache Le Bihan | 2026-11-05 | 1,534 | -- |
| Harness adapters: Safe RL for efficient agentic development | Younes B, Lysandre, and Nathan Habib | 2026-11-06 | 4,058 | -- |
| ToyBlocks: A controlled world for robot learning and evaluation | Kyle Wiggers | 2026-11-06 | 3,962 | -- |
| SuperCLUE November 2026: Category Leaders and the Full 19-Model Score Ranking | VIDRAFT_LAB | 2026-11-06 | 2,069 | -- |
| Egyptian and Nigerian English join the Open ASR Leaderboard | Eric Bezzam, Ashley Mo, and Aoi Otani | 2026-11-06 | 437 | -- |
| MOSS-Live: A Full-Duplex Real-Time Interaction System | Chen Yang | 2026-11-07 | 1,526 | -- |
| SafetyPulse: Catching Safety Drift During Fine-Tuning by Reading the Model's Refusal Circuit | purvansh joshi, Archit Mittal, and Anubhav Kiroula | 2026-11-08 | 4,558 | -- |
| Nemotron PII Japan: プライバシー保護に向けた日本語PIIオープンデータ | Masaya Ogushi, Atsunori Fujita, Vincent Gong, Kotaro Yamamoto, Colleen Ruan, Yoshi Suhara, Will Jennings, and Andre Manoel | 2026-11-09 | 462 | -- |
| Evaluating Privacy Protection and Practical AI Applications with 100,000 Synthetic Business Documents Across Eight Domains | Will Jennings, Masaya Ogushi, Atsunori Fujita, Vincent Gong, Kotaro Yamamoto, Yoshi Suhara, Colleen Ruan, and Andre Manoel | 2026-11-09 | 3,602 | -- |
| Nemotron-Personas-Finance-Japan: 日本の人口分布と金融コンテキストを捉える合成ペルソナデータセット | Atsunori Fujita, Masaya Ogushi, Vincent Gong, Kotaro Yamamoto, Yoshi Suhara, Will Jennings, and Yev Meyer | 2026-11-09 | 318 | -- |
| Qai x Hugging Face Hackathon | Aritra Roy Gosthipaty, Sayak Paul, Younes B, Niels Rogge, and Serge Habis | 2026-11-09 | 299 | -- |
| Nemotron-Personas-Finance-Japan: A Synthetic Dataset Capturing Japan's Demographics and Financial Context | Atsunori Fujita, Masaya Ogushi, Vincent Gong, Kotaro Yamamoto, Yoshi Suhara, Will Jennings, and Yev Meyer | 2026-11-09 | 1,336 | -- |
| Your Experts Have Partners. There's HOPE for Keeping Them Together | Alex M Tseng and Luca Zancato | 2026-11-09 | 2,709 | -- |
| Stop Paying the Embedding Tax: Why Simple BM25 + Seb Beats 8B Vector RAG on Quality, Speed, and Cost | Stas Veretennikov | 2026-11-10 | 2,830 | -- |
| Bring Your Own Expert! Extending MoE Models with New Domain Expertise | Fabian Klemm, Lars Reimann, Andreas Rabenstein, Henrik Klagges, and Robert Dahlke | 2026-11-10 | 1,909 | -- |
| MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification | Jiaju Ma, Ashvini Kumar Jindal, Chuhua Wang, and Sumithra Bhakthavatsalam | 2026-11-10 | 4,771 | -- |