19 stories tagged Simulation
NVIDIA has open-sourced a suite of simulation tools for training AI in realistic physical environments, aiming to accelerate robotics and automation research. The tools include advanced physics engines and high-fidelity 3D environments, making high-quality simulation accessible to more developers.
With traditional language model training hitting diminishing returns, researchers are turning to simulated 3D worlds to teach AI agents common sense, planning, and physical reasoning — skills that text alone struggles to impart.
Researchers created a new system to train AI agents in realistic simulations, using reinforcement learning and reward shaping to improve multi-step decision-making.
LeRobot v0.6.0 is an open-source library focused on real-world robotics, providing datasets, models, and simulation tools for reproducible AI research. It is not an image generation tool.
Researchers created a test to evaluate how well AI agents can use scientific software for chemistry simulations. The benchmark, PHREEQC-MCQ-200, challenges AI to solve 200 multiple-choice questions using a geochemistry tool called PHREEQC.
Researchers developed Agri-SAGE, an AI system that combines agricultural science with real-time conditions to give farmers better advice. It uses simulations to make recommendations that are both scientifically sound and practical.
Researchers are using AI to make it easier to find and reuse simulation models. This could speed up scientific work and reduce redundancy. The study explores how different AI techniques affect the search process.
Researchers created a simulated startup to see if AI could handle day-to-day business decisions. The experiment reveals both the potential and limitations of AI in management roles.
Researchers created an AI system that mimics human driving styles by conditioning on explicit human demonstrations. This could make driving simulations more realistic and safer.
Scientists are using AI models like Codex to create detailed black hole simulations. This helps them study extreme physics and test Einstein’s theory of general relativity in ways that were previously impossible.
Decart has launched Oasis 3, a real-time world model that generates photorealistic driving environments for autonomous vehicle testing. The tool is now available via API for developers to build on, though it comes with some important caveats.
Researchers introduced a new benchmark, UnpredictaBench, to evaluate whether large language models (LLMs) can capture true underlying distributions rather than collapsing to a single plausible answer. This is critical as AI is increasingly used as a substitute for real entities in economic simulations and other modeling tasks.
Researchers built a multi-agent economy simulation using a small AI model with just 3 billion parameters. This shows how powerful even modest-sized models can be for complex tasks.
Researchers created AbaqusAgent, a multi-agent AI system that automates finite element analysis (FEA) for engineering. This could make advanced simulations accessible to non-experts, speeding up product design and reducing errors.
Researchers developed a new AI system to simulate how hospitals react to policy changes. This could help design better healthcare systems by predicting real-world impacts.
NVIDIA has fine-tuned its Cosmos Predict 2.5 model to generate realistic robot videos. This advancement could revolutionize robot training and simulation.
Researchers introduce OpenFlo, an AI agent that simulates human web interactions to evaluate usability. Unlike traditional tools, OpenFlo grounds actions and observations for coherent user journey tracing.
Researchers have developed a method to explore high-dimensional PDE solution spaces using latent foundation models. This approach promises to revolutionize the study of complex physical phenomena by enabling automated, large-scale exploration.
A new synthetic sandbox environment has been created to train machine learning engineering agents. This could revolutionize how AI systems are developed and tested.