报名 GTC 期间的全天 AI 实战培训、迷你实战课程和 NVIDIA 认证

This hands-on lab introduces Newton, a GPU-accelerated physics engine. Then we'll integrate Newton with Isaac Lab, showing how they can work together in robot-learning workflows. You'll configure tasks to run on Newton, and train and evaluate policies in Isaac Lab with Newton providing high-fidelity, high-throughput physics. You'll leave knowing how to use Newton for more realistic robotics simulation.

We'll walk you through how to turn financial services workflows into end‑to‑end AI agents, covering orchestration, tools, retrieval, and guardrails tailored to domain-specific applications in the financial services industry (FSI). Using NVIDIA’s NeMo Agent Toolkit and Blueprints, you'll get hands on to building multi‑agent systems that support use cases such as investment research and agentic commerce.

Our workshop highlights proven strategies for tabular data developed by NVIDIA’s Kaggle grandmasters, who have earned top honors in hundreds of international data science competitions. You'll practice rapid electronic design automation (EDA), large-scale feature engineering, model building, ensembling, and pseudo-labeling — all accelerated with GPUs for faster experimentation and better accuracy.

In this training lab, we'll demonstrate how state-of-the-art reasoning vision-language-actions (VLAs) models, like Alpamayo R1, can be used as part of a safety evaluation pipeline ready for next-generation, end-to-end AI-powered autonomous vehicles (AVs). Learn how to use these powerful reasoning models to aid in data curation for safety validation, using these models to mine the NVIDIA Physical AI Dataset to identify key scenarios to target with additional testing.