| Building the Open Agent Ecosystem Together: Introducing OpenEnv |
Joseph Spisak, Davide Testuggine, Zach Wentz, Pierre Andrews, Sanyam Bhutani, Hamid Shojanazeri, Pankit Thapar, Emre Guven, Lewis Tunstall, and Vaibhav Srivastav |
Oct 23, 2025 |
1117 |
- |
| VibeGame: Exploring Vibe Coding Games |
Dylan Ebert |
Sep 29, 2025 |
1777 |
- |
| Llama‑Embed‑Nemotron‑8B Text Embedding Model Ranks First on Multilingual MTEB Leaderboard |
Yauhen Babakhin, Radek Osmulski, Ronay Ak, Gabriel de Souza Pereira Moreira, and Mengyao Xu |
Oct 21, 2025 |
706 |
- |
| Nemotron’s Open Secret: Accelerating AI Development with Open Models, Data, and Recipes |
Bryan Catanzaro and Jonathan Cohen |
Oct 22, 2025 |
1684 |
- |
| Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm |
You Liang Tan, Fengyuan Hu, Oyindamola Omotuyi, Oluwaseun Doherty, Chitoku Yato, and Shane Reetz |
Jun 11, 2025 |
1902 |
- |
| Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text |
Solomatin Roman, Kenneth C. Enevoldsen, and Isaac Chung |
Oct 20, 2025 |
2320 |
- |
| huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning |
Lucain Pouget, Célina Hanouti, Lysandre, and Julien Chaumond |
Oct 27, 2025 |
2139 |
- |
| Supercharge your OCR Pipelines with Open Models |
merve, Aritra Roy Gosthipaty, Daniel van Strien, Hynek Kydlicek, Andres Marafioti, Vaibhav Srivastav, and Pedro Cuenca |
Oct 21, 2025 |
3544 |
- |
| Cosmos Predict 2.5 & Transfer 2.5: Evolving the World Foundation Models for Physical AI |
Prachi Mishra |
Oct 28, 2025 |
921 |
- |
| Hugging Face and VirusTotal collaborate to strengthen AI security |
Adrien Carreira and Bernardo Quintero |
Oct 22, 2025 |
507 |
- |
| Voice Cloning with Consent |
Margaret Mitchell and Lucie-Aimée Kaffee |
Oct 28, 2025 |
1394 |
- |
| Google Cloud C4 Brings a 70% TCO improvement on GPT OSS with Intel and Hugging Face |
Jiqing.Feng, Matrix Yao, Ke Ding, and Ilyas Moutawwakil |
Oct 16, 2025 |
1374 |
- |
| Advancing Predictive ADMET Modeling Through Community-Driven Science: The ExpansionRx-OpenADMET Blind Challenge |
Georgia Channing and Hugo MacDermott |
Oct 27, 2025 |
943 |
- |
| Vision Tokens vs Text Tokens: Understanding the 10× Compression |
Yi Cui |
Oct 22, 2025 |
535 |
- |
| Projected Abliteration |
Jim Lai |
Oct 25, 2025 |
2218 |
- |
| Streaming datasets: 100x More Efficient |
Andres Marafioti, Quentin Lhoest, ben burtenshaw, Pedro Cuenca, and merve |
Oct 27, 2025 |
1306 |
- |
| Sentence Transformers is joining Hugging Face! |
Tom Aarsen |
Oct 22, 2025 |
1011 |
- |
| Unlock the power of images with AI Sheets |
Ame Vi, Daniel Vila, Francisco Aranda, Damián Pumar, Leandro von Werra, and Thomas Wolf |
Oct 21, 2025 |
1495 |
- |
| Get your VLM running in 3 simple steps on Intel CPUs |
Ezequiel Lanza, Helena, Nikita, Ella Charlaix, and Ilyas Moutawwakil |
Oct 15, 2025 |
1479 |
- |
| Introducing RTEB: A New Standard for Retrieval Evaluation |
Frank Liu, Kenneth C. Enevoldsen, Solomatin Roman, Isaac Chung, Tom Aarsen, and Fődi, Zoltán |
Oct 01, 2025 |
2833 |
- |
| Building a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac |
Steven Palma and Andres Diaz-Pinto |
Oct 29, 2025 |
1115 |
- |
| GSMA Open-Telco LLM Benchmarks 2.0: The first dedicated LLM Evaluation for Telecoms |
Lina Bariah, Antonio De Domenico, Louis Powell, Mohamed Sana, Merouane Debbah, Mark Austin, Farbod Tavakkoli, George George, Nicola Piovesan, Simone Mangiante, cherrared, Sumeyye Bas, GHADA SOLIMAN, Dilara Zeynep Gurer, Laszlo Suto, and Pierre Wang |
Oct 20, 2025 |
3090 |
- |
| NVIDIA Isaac GR00T in LeRobot |
lior ben horin, Kartik S, Aravindh Shan, Asawaree, and You Liang Tan |
Oct 28, 2025 |
1182 |
- |
| LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR |
Said Taghadouini, Baptiste Aubertin, and Adrien Cavaillès |
Oct 23, 2025 |
4470 |
- |
| Granite 4.0 Nano: Just how small can you go? |
Kate Soule and Rameswar Panda |
Oct 28, 2025 |
544 |
- |
| How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare |
Asawaree |
Oct 28, 2025 |
1078 |
- |
| Can Your LLM Think Like a Professional? Introducing ProfBench |
Zhilin Wang, Jaehun Jung, Ximing Lu, Shizhe Diao, jiaqiz, VivienneZhang, Nik Spirin, and Dong |
Oct 28, 2025 |
1337 |
- |
| 🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI |
Maarten Van Segbroeck |
Oct 28, 2025 |
988 |
- |
| SOTA OCR on-device with Core ML and dots.ocr |
Christopher Fleetwood and Pedro Cuenca |
Oct 02, 2025 |
1910 |
- |
| Australian-made LLM beats OpenAI and Google at legal retrieval |
Umar Butler, Abdur-Rahman Butler, and Adrian Lucas Malec |
Oct 23, 2025 |
930 |
- |
| NVIDIA Releases 8 Million Sample Open Dataset and Tooling for OCR, Image Reasoning, Image and Video QA Tasks |
Yao Xu, Timo Roman, Lukas Voegtle, Philipp Fischer, Amala Sanjay Deshmukh, Kateryna Chumachenko, and Jarno Seppänen |
Oct 28, 2025 |
1014 |
- |
| Promoter-GPT: Writing DNA Instructions with Language Models |
Adele de Hoffer |
Oct 22, 2025 |
3509 |
- |
| LeRobot v0.4.0: Super Charging OSS Robotics Learning |
Steven Palma, Michel Aractingi, Pepijn Kooijmans, Caroline Pascal, Jade Choghari, Francesco Capuano, Adil Zouitine, Martino Russi, and Thomas Wolf |
Oct 24, 2025 |
1980 |
- |
| KV Caching Explained: Optimizing Transformer Inference Efficiency |
Hafedh Hichri |
Jan 30, 2025 |
1230 |
- |
| Why Did MiniMax M2 End Up as a Full Attention Model? |
MiniMax |
Oct 30, 2025 |
1640 |
- |
| The World’s First and Best Speed Painting Software |
xing |
Oct 29, 2025 |
1368 |
- |
| 3+ Years of ML & Society at Hugging Face 🤗🤝🧑🤝🧑 |
Yacine Jernite, Giada Pistilli, Lucie-Aimée Kaffee, and Sasha Luccioni |
Oct 29, 2025 |
807 |
- |
| Nemotron-Personas-USA: Synthesized Data for Sovereign AI |
Will Jennings, Dane Corneil, and Yev Meyer |
Oct 28, 2025 |
630 |
- |
| svara-TTS — Open Multilingual TTS for India’s Voices |
Aditya Chhabra |
Oct 27, 2025 |
1626 |
- |
| What makes good reasoning data |
MiniMax |
Oct 30, 2025 |
629 |
- |
| On the Shifting Global Compute Landscape |
Tiezhen WANG and Irene Solaiman |
Oct 29, 2025 |
3172 |
- |
| Aligning to What? Rethinking Agent Generalization in MiniMax M2 |
MiniMax |
Oct 30, 2025 |
1103 |
- |
| Evaluate Your Own RAG: Why Best Practices Failed Us |
Charles AZAM, Antoine Hoorelbeke, Antoine Guyot, Maxence Leclercq, and Jérémy PICOSSON |
Nov 05, 2025 |
3569 |
- |
| Ultra-Long Sequence Parallelism: Ulysses + Ring-Attention Technical Principles and Implementation |
Exploding Gradients |
Sep 16, 2025 |
3586 |
- |
| DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge |
Yihua Zhang |
Feb 07, 2025 |
2499 |
- |
| ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases |
Quentin Macé, Antonio Loison, Antoine EDY, Victor Xing, and Gautier Viaud |
Nov 05, 2025 |
2524 |
- |
| Classement compar:IA : des votes des utilisateurs au classement participatif des modèles |
compar:IA |
Nov 03, 2025 |
1821 |
- |
| Llasa Goes RL: Training LLaSA with GRPO for Improved Prosody and Expressiveness |
Steven Zheng |
Nov 05, 2025 |
1120 |
- |
| Running Large Transformer Models on Mobile and Edge Devices |
MtugrulKaya |
Nov 03, 2025 |
6026 |
- |
| TorchSim: A new PyTorch-based molecular dynamics engine |
Davide Sarpa |
Oct 31, 2025 |
3592 |
- |
| The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix |
Asankhaya Sharma |
Nov 03, 2025 |
1833 |
- |
| ⚡ Power, Heat, and Intelligence ☁️ - AI Data Centers Explained 🏭 |
Boris Gamazaychikov and Sasha Luccioni |
Nov 05, 2025 |
2952 |
- |
| Small Language Models (SLM): A Comprehensive Overview |
John Johnson |
Feb 22, 2025 |
1456 |
- |
| Toward Community-Governed Safety |
Giada Pistilli and Lucie-Aimée Kaffee |
Nov 03, 2025 |
681 |
- |
| From GRPO to DAPO and GSPO: What, Why, and How |
Yihua Zhang |
Aug 09, 2025 |
5841 |
- |
| Budget Alignment: Making Models Reason in the User’s Language |
Shan Chen, Jirui Qi, and Zidi Xiong |
Nov 04, 2025 |
3207 |
- |
| Who Routes LLM Routers? RouterArena: Building the Evaluation Foundation for LLM Routing |
Yifan Lu, Riksin, Jiayi Yuan, Bruce Cui, SJ Chang, Hongyi Liu, and Jiarong Xing |
Nov 11, 2025 |
1552 |
- |
| SYNTH: the new data frontier |
Pierre-Carl Langlais |
Nov 10, 2025 |
1995 |
- |
| Effective Prompting for Generative Vision Models |
Sara Han Díaz and Bertrand Charpentier |
Nov 10, 2025 |
1013 |
- |
| 🌳 QAT: The Art of Growing a Bonsai Model |
Yi Cui |
Nov 09, 2025 |
1267 |
- |
| Norm-Preserving Biprojected Abliteration |
Jim Lai |
Nov 06, 2025 |
2135 |
- |
| Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face |
Daniel Voigt Godoy |
Feb 11, 2025 |
3900 |
- |
| Mastering Tensor Dimensions in Transformers |
Hafedh Hichri |
Jan 12, 2025 |
2555 |
- |
| Text-to-image Architectural Experiments |
David Bertoin, Jon Almazán, and Roman |
Nov 13, 2025 |
3525 |
- |
| Exploring Direct Tensor Manipulation in Language Models: A Case Study in Binary-Level Model Enhancement |
Tensor-Slayer |
Nov 07, 2025 |
1843 |
- |
| We’re open-sourcing our text-to-image model and the process behind it |
Jon Almazán, David Bertoin, and Roman |
Nov 12, 2025 |
1110 |
- |
| Building for an Open Future - our new partnership with Google Cloud |
Jeff Boudier and Simon Pagezy |
Nov 13, 2025 |
869 |
- |
| ⛳ Optimizer: What Does It Do and Why We Need It |
Yi Cui |
Nov 12, 2025 |
1313 |
- |
| To Think or Not to Think: A Router for Hybrid LLMs |
Amir Mohseni |
Nov 16, 2025 |
2137 |
- |
| The Heterogeneous Feature of RoPE-based Attention in Long-Context LLMs |
Xiaoran Liu (SII) |
Nov 15, 2025 |
1834 |
- |
| The Pharmome Map: a comprehensive public dataset for drug-target interaction modeling |
Elaine McVey Houskeeper and Georgia Channing |
Nov 18, 2025 |
1662 |
- |
| Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models |
Torsten Scholak, Oleksiy Ostapenko, Raymond Li, Luke Kumar, and Joel Lamy-Poirier |
Nov 19, 2025 |
1709 |
- |
| Easily Build and Share ROCm Kernels with Hugging Face |
Abdennacer Badaoui, Daniel Huang, colorswind, and Zesen Liu |
Nov 17, 2025 |
3120 |
- |
| Join the AMD Open Robotics Hackathon |
Eric Ma and Guruprasad MP |
Nov 13, 2025 |
506 |
- |
| PEFT: Parameter-Efficient Fine-Tuning Methods for LLMs |
Samuel Lima Braz |
Jan 24, 2025 |
8770 |
- |
| AI Model Optimization More Flexible Than Ever |
Johanna Sommer, Sara Han Díaz, and Bertrand Charpentier |
Nov 17, 2025 |
725 |
- |
| Visualizing How VLMs Work |
Hafedh Hichri and Ed Daniels |
Oct 07, 2025 |
1851 |
- |
| 🧠 SQaLe: Enabling new Text-to-SQL models with our massive dataset |
Cornelius Wolff, Daniel Gomm, and Madelon Hulsebos |
Nov 19, 2025 |
944 |
- |
| Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms |
Mattt |
Nov 20, 2025 |
1326 |
- |
| Introducing Cogito v2.1 |
Deep Cogito Team |
Nov 19, 2025 |
1067 |
- |
| Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks |
Eric Bezzam, Steven Zheng, Eustache Le Bihan, and Vaibhav Srivastav |
Nov 21, 2025 |
936 |
- |
| 20x Faster TRL Fine-tuning with RapidFire AI |
Kamran Bigdely, Arun Kumar, and Quentin Gallouédec |
Nov 21, 2025 |
1198 |
- |
| How to make NeuTTS-air generate over 200 seconds of audio in a single second. |
Yatharth Sharma |
Nov 21, 2025 |
792 |
- |