NVIDIA AI

Vidit Gujrathi, Indian chess grandmaster and Chess Olympiad gold medalist, entered the Nous Research × NVIDIA × Stripe Hermes Agent Accelerated Business Hackathon with a sharp insight: chess engines tell you the best move, but grandmasters are human – they don't always play it. So he built "Kibitz": a human move predictor for live chess broadcasts, using an NVIDIA RTX 5080. Then he handed operations to a Hermes Agent powered by Nemotron. The agent onboards broadcast clients, handles billing, narrates matches, tracks inference costs, and manages its own P&L – without Vidit needing to be involved in the day to day minutiae of the agent. In this session, Vidit walks through how he designed Kibitz end-to-end and structured the Hermes Agent to run a real business autonomously. What you'll learn: How to train a domain-specific prediction model on NVIDIA hardware How to design a Hermes Agent that handles onboarding, billing, and operations end-to-end How Nemotron fits into an agentic pipeline as a narration and reasoning layer How to go from a working model to a self-operating AI business Building with Hermes or Nemotron? Bring your questions, and our chess grandmaster guest will be answering them live.

"Data stops being something you collect. It becomes something you compute." At #SIGGRAPH2026, Ming-Yu Liu, VP of NVIDIA's Cosmos Lab, laid out why world models are the data engine of physical AI. Plus, he announced Cosmos-Dreams, a neural closed-loop simulator, and showed off a full demo of it in action. You can watch the full keynote here: https://vist.ly/5cwd8

NVIDIA DeepStream is an open-source streaming analytics tool and skills for real-time, AI-powered multi-sensor processing across video, audio, and images. DeepStream 9.1 accelerates vision AI development with agentic skills that help developers move from natural language prompts to production-ready pipelines. Learn how NVIDIA DeepStream 9.1 accelerates edge vision AI development with JetPack 7.2 support, open-source workflows, and new agentic skills for building video ingestion and analytics pipelines from natural language prompts. In this livestream, we will show how developers can use DeepStream 9.1 skills with coding agents like Codex or Claude Code to automate camera calibration, generate pipeline configurations, and deploy multi-camera 3D tracking applications that maintain consistent object IDs across camera views.

Customizing open models doesn't have to mean managing your own GPU cluster. In this livestream, we walk through a complete hosted reinforcement learning run on Nemotron 3 Nano — from a cold start to a downloadable LoRA adapter — using Prime Intellect Lab. Local setup takes about five minutes. Prime Intellect handles the rest. The session follows the same three-step loop: get a baseline, train with RLVR, and reevaluate under identical conditions. You'll see how to configure and launch a LoRA RL job, read reward curves and rollouts to understand what the model actually learned, and deploy the adapter for inference. You can also apply the same workflow to Nemotron 3 Super and Ultra, and extend it to real software engineering tasks. What you'll learn: - How to install the Prime CLI, set up a Lab workspace, and run a baseline evaluation in minutes - How to configure and launch a hosted LoRA RL training job on Nemotron 3 Nano - How to read reward curves and rollout traces to distinguish learning from reward hacking - How to deploy a LoRA adapter and rerun evaluation to measure actual improvement How to apply this workflow to Nemotron 3 Super and Ultra, and scale to harder tasks Ready to start training your own open models? Bring your questions live.

This session shows developers how to build and run their first local GenAI app on NVIDIA Jetson using open-source models such as Gemma and Qwen directly on device. We’ll teach different ways of running inference with Ollama, vLLM, and llama.cpp, including when each framework makes sense for rapid local prototyping, production-style serving, or lightweight edge deployment. Along the way, we’ll share best practices for model choice, quantization, and performance tuning. In this stream, you will learn how to deploy open-source AI models on NVIDIA Jetson — no cloud required, from first launch to production-ready serving. We'll cover: - Getting models running on NVIDIA Jetson — spin up popular OSS models (open-source large language models (LLMs) like Gemma and Qwen (LLMs and VLMs) using Ollama or vLLM on Jetson hardware and verify they're working end-to-end. - Choosing the right inference engine — understand the practical tradeoffs between Ollama for rapid local prototyping, vLLM for higher-throughput serving, and llama.cpp, so you can pick the right tool for your use case. - NVIDIA Jetson-specific serving strategies — walk through the real decisions behind model choice, containers, and performance tuning tailored for Orin and Thor, including what works, what doesn't, and why. - Performance fundamentals — get introduced to quantization and speculative decoding: what they are, how they work, and when to reach for them on edge hardware. - Real-world application — see a live demo of the Reachy Mini assistant, an end-to-end example of OSS models running in real time.

Built first in a virtual world, then in Fort Worth. 🏭 Wistron's Michael Chien shows how its factory agent brings data into a digital twin built with NVIDIA Omniverse libraries and runs Nemotron locally, with plans to post-train it on Wistron’s technical documents.

10 million downloads and counting for NVIDIA Cosmos models on Hugging Face. 🤗 This milestone belongs to the developers and researchers using open world foundation models to build robots, autonomous vehicles and other physical AI systems. Thank you for downloading, experimenting, and building with us. 💚 Explore NVIDIA Cosmos → https://vist.ly/5cnnc

AI security improves when organizations share research, tools and real-world experience. We’re joining industry leaders, including NVIDIA, in the Open Secure AI Alliance to help organizations identify and address software vulnerabilities and strengthen critical systems. Learn more: nvda.ws/4pD8Fc5

I’m super excited to have been inducted into the list of PSF Fellows! https://lnkd.in/giqDTWZV I’ve posted a few thoughts on what Python means to me on my blog: https://lnkd.in/g63bQ5eE