Hugging Face

Hugging Face (Twitter) RT @LeRobotHF: 🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot! This is the result of a great collaboration between the @huggingface LeRobot team and @NVIDIARobotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action prediction

Hugging Face (Twitter) RT @ErikKaum: Deploy your favorite OCR models with few-clicks directly from Hugging Face 🔥 📷we've added the latest bleeding edge OCR models to the Inference Endpoints catalog to make it easy for you to get started! links 👇

Hugging Face (Twitter) RT @HarveenChadha: a bunch of OCR models released in past few weeks: ~ deepseek-ocr-3b ~ olmo-ocr-2-7b ~ chandra-ocr-8b ~ nanonets-ocr2-3b ~ paddleocr-vl-0.9B ~ qwen3-vl-dense/moe (general vlm) ~ dots.ocr-3b Will be dropping a detailed comparison soon

Hugging Face (Twitter) RT @bquintero: It’s been a pleasure working side by side with @julien_c and the @huggingface team to make this happen... and this is just the beginning. Thanks for the great collaboration! https://huggingface.co/blog/virustotal

Hugging Face (Twitter) RT @TheAhmadOsman: HUGE > we have a new #1 on the > MTEB Embedding Benchmark Leaderbord llama-embed-nemotron-8b > beats Gemini, Qwen3, Linq, GTE > fits on ONE RTX 5090 > 4096 dims, 32k ctx > 69.46 avg across tasks > multilingual bi-encoder, zero-shot across retrieval, rerank, STS, classification

Hugging Face (Twitter) RT @HuggingPapers: Qwen just released Qwen3-VL on Hugging Face The most powerful vision-language model in the Qwen series, with comprehensive upgrades across text understanding, visual reasoning, and long context video analysis. From GUI operations to 1M context.

Hugging Face (Twitter) RT @Xianbao_QIAN: PokeeResearch 7B looks strong on deep research. Link on @huggingface below

Hugging Face (Twitter) RT @vanstriendaniel: DeepSeek-OCR just got @vllm_project support 🚀 Currently processing @natlibscot's 27,915-page handbook collection with one command: Processing at ~350 images/sec on A100 Using @huggingface Jobs + @astral_sh uv - zero setup batch OCR! Will share final time + cost when done!

‌Hugging Face (Twitter) RT @Pokee_AI: Open. Source. SOTA. Deep. Research. 🚀 Today, we’re releasing PokeeResearch-7B, a SOTA open-source deep research agent that outperforms all other 7B deep research agents. And, we are open-sourcing both the weights and inference code on @huggingface! We're additionally excited to have partnered with vLLM @vllm_project, SGLang @sgl_project, and verl @verl_project on training and inference pipelines. We can’t wait to see what you all build with PokeeResearch! 🤗• Hugging Face Model: 🌐• Webpage: https://pokee.ai/deepresearch-preview 📋• ArXiv: arxiv.org/pdf/2510.15862 🔗• Github Repo: https://github.com/Pokee-AI/PokeeResearchOSS

Hugging Face (Twitter) RT @IBMResearch: Now available on @huggingface, the new dataset of 1.5 million task scenarios, field-tested and open-sourced by researchers from @IBM and the @UW, is designed to improve how agents interact with the world and get things done: ibm.co/6011BK7GR

Hugging Face (Twitter) RT @ClementDelangue: We just released the beta version of the open-source software for Reachy Mini! It means that anyone, thanks to the amazing @GoogleDeepMind mujoco simulation platform, can start building @huggingface spaces, datasets and models, even if you haven't received your robot yet. Super excited to try to make Reachy Mini the hardware platform for AI builders and unleash the power of open-source and collaboration for robotics! 🦾🦾🦾

Hugging Face (Twitter) RT @gui_penedo: New dataset release: 🌐FineWiki This is an updated and better extracted version of Wikipedia, covering 325+ languages. Unlike the old dataset from 2023, we kept all the math content, tables, properly rendered templates, and extracted key facts. Examples and highlights below.