MathWorks, the leading developer of mathematical computing software, will showcase how engineers and scientists can use MATLAB® and Simulink® to design, verify, and deploy AI-driven systems for safety-critical applications, electrification, and robotics at the Neural Information Processing Systems (NeurIPS) Conference, the world’s premier event for machine learning and computational neuroscience. NeurIPS attracts thousands of researchers, data scientists, and engineers from academia and industry, with attendees representing over 70 countries and a strong mix of AI practitioners, graduate students, and technology leaders. MathWorks (Booth #732) will demonstrate how engineers and scientists can use MATLAB® and Simulink® to design, verify, and deploy AI-driven engineered systems.
“NeurIPS is where cutting-edge AI research meets real-world impact,” said Lucas Garcia, AI Product Manager at MathWorks. “Being part of this event highlights a dedication to connecting academic innovation with industry confidence. We’ll be showing attendees how MATLAB and Simulink support the journey from prototype to production—whether the focus is on generative AI, autonomous systems, embedded AI deployment, or incorporating AI into engineered systems—using Model-Based Design.”
EXHIBITOR PRESENTATION
Date & Time: Tuesday, December 2, 3:00 pm PDT
Location: Exhibit Hall A, B
Generative AI has made headlines with fluent text and clever code, setting new benchmarks in creativity and performance. But in safety-critical domains like aerospace, automotive, and healthcare, the challenge is different: ensuring that AI systems behave reliably and safely under all possible operating conditions.
In this talk, Lucas Garcia explores the gap between academic breakthroughs and industrial trust, and shows how formal verification, explainability, and runtime assurance can turn black-box models into certifiable systems. Drawing on the company's experience working with engineers and scientists in developing AI-enabled safety-critical systems, he’ll demonstrate how to verify robustness, detect out-of-distribution inputs, and meet emerging safety standards—across models in PyTorch, ONNX, and MATLAB.
EXHIBIT BOOTH DEMOS
Booth #732
MathWorks will present three interactive demonstrations that show how MATLAB and Simulink accelerate AI development for engineering applications.
AI-Based Virtual Sensor for Battery State-of-Charge Estimation
MathWorks illustrates how AI can enhance battery management systems by estimating state-of-charge (SOC) using virtual sensors. Engineers can simulate battery behavior under various operating conditions, compress models for efficient deployment, and generate production-ready code using MATLAB and Simulink. The workflow integrates AI with physics-based models to deliver accuracy and reliability for electric vehicle and energy storage systems. Attendees will see how these tools simplify the transition from concept to embedded deployment, reducing development cycles and improving system performance.
RTM Pose Estimation Deployed to Embedded GPUs
This demonstration highlights real-time pose estimation for robotics and autonomous systems. Using AI features in MATLAB, the demo provides insights into the latest research on bringing models from PyTorch or ONNX into MATLAB, optimizing the model for deployment, and generating code for NVIDIA Jetson AGX Orin hardware. Visitors will see how open-source frameworks work seamlessly with MATLAB workflows, supporting rapid prototyping and deployment of AI models in resource-constrained environments. This end-to-end process demonstrates a commitment to helping engineers build robust, efficient AI solutions for practical applications using Model-Based Design.
MCP with MATLAB
MathWorks will demonstrate how an LLM MCP client integrates with MATLAB MCP Core Server to streamline data cleanup, create visualizations, and build simple machine learning models. The demo highlights common data analysis workflows and can be easily reset for repeated use. Attendees will see how these tools accelerate the transition from concept to embedded deployment, reducing development cycles and enhancing system performance.
