✨Just released: NVIDIA Nemotron post-training multi-lingual dataset ✨ We... expanded permissive post-training dataset with addition of synthetically translated reasoning traces. ✋ Five new languages 💪 World class reasoning traces 🤗 Learn more: 📥 Download:show more

Better training data. Faster training cycles. Any language, any... domain. AISingapore used Adaption to enhance dataset quality and expand training dataset size via localization across five low-resource Southeast Asian languages.show more

As a supporter of the open weights ecosystem, we're... proud to be a post-training partner for NVIDIA Nemotron. We post-train Nemotron models for customer use cases, de-risk mainline RL runs on our AC2 platform and training stack, and contribute aggregate workload statistics for inference benchmarking. This is how open models get better, and we're excited to keep working closely with NVIDIA AI.show more

💚🤗💚 Jensen showing Hugging Face during GTC keynote, where... NVIDIA AI dropped amazing new open models, datasets and blogs! Some of my favorites, links in comments: 🧠 Nemotron 3 Super 120A12B - Reasoning LLM 🏥 Open-H-Embodiment - Healthcare Robotics Dataset 🩻 Cosmos-H-Surgical-Simulator - World Foundation Model 🚕 Alpamayo 1.5 - Autonomous Vehicle Model and Datasets 🕺 Kimodo v1 - Generate body movement from prompts! And SO MUCH MORE to explore atshow more

Vibes post training ✨💕

Introducing Alpamayo 1.5. Based on community feedback, we’ve updated... our 10B-parameter chain-of-thought reasoning VLA model to be a more interactive and steerable engine for autonomous vehicle development. Built on the Cosmos-Reason2 VLM backbone, this release adds support for navigation guidance and flexible camera configurations while providing new post-training scripts for model adaptation. 🤗 Learn more:show more

NVIDIA Nemotron 3 Nano Omni, a new multimodal reasoning... model, is now live on Jetson AI Lab and unifies vision, audio, and language into a single reasoning loop. 🙌 Power your NemoClaws by running this model with Ollama, vLLM and other inference frameworks on NVIDIA Jetson hardware. Try it ➡️show more

We released a new model 🎉 !!! Firefly Image... 2 !!!! As a scientist I am in disbelief that such model is possible with a small dataset as we had. We compensated artists for training it. We worked very hard on it. Please, enjoy! #AdobeMaxshow more

Google just released the AlphaEarth Foundations with 64 dimensions... of satellite embeddings at 10-m resolution at the global scale! It is very interesting! Check it out Blog post: Dataset: Paper: #AI #geospatial #remotesensing #geoaishow more

Palantir CTO Shyam Sankar says he almost felt gaslit... when a vanilla Nemotron beat the frontier with no post-training, because the benchmarks are wrong. "I literally almost felt gaslit when within 24 hours of getting Nemotron up with no post-training, this is vanilla Nemotron Ultra, it did better than Frontier." "If you just looked at the numbers you would say, well, it's nowhere near the Frontier." "That shouldn't even be possible." "But of course, the benchmarks are wrong."show more

Today we’re releasing SAIR, the Structurally Augmented IC50 Repository.... SAIR is the Largest Open-Sourced Binding Affinity Dataset with Cofolded 3D Structures. It includes more than 5 million protein-ligand structures, generated using our Large Quantitative Models and labeled with binding affinity data. By providing this unprecedented scale of structure-activity data, we aim to enable researchers to train and evaluate new AI models for drug discovery, bridging the historical gap between molecular structures and drug potency prediction. The SAIR dataset was created using the NVIDIA DGX Cloud and is now publicly available on the Google Cloud Platform. Access and build with SAIR today! 📰Read the Press Release: 📥Learn More and Download the Dataset at #DrugDiscovery #LQMs #SAIR #AIforScience #SandboxAQshow more

NVIDIA says Codex post-trained Cosmos 3 Nano from 54.41%... to 93.35% accuracy in one day - with two prompts. The experiment used Toyota’s Woven Traffic Safety dataset: 8,000+ training and validation samples for four-choice video reasoning. Using NVIDIA TAO agent skills, Codex autonomously: Detected and patched missing video metadata Ran the zero-shot baseline Generated LoRA configurations Launched training and evaluation Ran an AutoML hyperparameter sweep Reported the best model One LoRA run reached 87.14% after roughly 30 minutes on eight A100 GPUs. A second prompt launched 43 parallel AutoML trials across multiple A100 nodes, reaching 93.35% after 19.5 hours. NVIDIA says LoRA required roughly seven times fewer GPU-hours than full-parameter training. Agent skills are becoming the interface through which general coding agents operate highly specialized ML infrastructure.show more

We just released an open-source framework that makes it... easy to build visual reasoning agents (with GRPO).show more

🚨New dataset + challenge #EMNLP2024🚨 We release ASL STEM... Wiki: the first signing dataset of STEM articles! 📰 254 Wikipedia articles 📹 ~300 hours of ASL interpretations 👋 New task: automatic sign suggestion to make STEM education more accessible 🧵show more

🍌 Just released NanoBanana Pro LoRA Dataset Generator with... fal Finally an easy way to create training datasets for: • Flux 2 • Z-Image • Qwen Image Edit • Any image-to-image model ✨ Uses Nano Banana Pro API on fal 🌐 100% browser-based - no server needed ⚡ Parallel generation for speed 🔗 Try it live: 💻 Code:show more

📢📢𝐍𝐞𝐑𝐒𝐞𝐦𝐛𝐥𝐞 𝐯𝟐 𝐃𝐚𝐭𝐚𝐬𝐞𝐭 𝐑𝐞𝐥𝐞𝐚𝐬𝐞📢📢 Head captures of 7.1MP from... 16 cameras at 73fps: * More recordings (425 people) * Better color calibration * Convenient download scripts The new version of our dataset adds 156 participants for a total of 425 different people. In its entirety, the dataset provides now 65 million images from over 15 hours of diverse human facial expression performances. We improved the color consistency of the recorded images with a better color calibration procedure. As a result, 3D reconstructions with images from the NeRSemble dataset should become better and look more realistic. Finally, we made it much easier to download the recordings with our new download repository. It now just takes a single command to download all frontal hair shake videos of all participants or to download all recordings of a single participant. Check it out: Awesome work by Tobias Kirschstein Simon Giebenhain !!!show more

Skild AI's new S1 robot foundation model helps robots... learn previously unseen tasks from a single video demonstration. 🤖 See how NVIDIA technology supports S1 from training and simulation to real-world deployment. Learn more ➡️show more

Post-training…

Today, we enter a new era of intelligence with... Gemini 3. ✨ Our most intelligent model helps you bring any idea to life — offering state-of-the-art reasoning with unprecedented depth and nuance.show more