Building on the Zhejiang University course platform for “Signals and Systems,” this presentation examines the instructional integration of MATLAB Live Scripts and AI. To support the systematic alignment of foundational theory with modern engineering tools, the speaker has developed a portable, highly interactive, and end-to-end live-script courseware spanning key laboratory modules, including 1D/2D convolution; audio and image filtering; the Gibbs phenomenon; modulation and demodulation; FFT; numerical solution of differential/difference equations; and filter design. These activities are designed to render mathematical expressions and waveform behavior tangible and experiment-driven, thereby strengthening conceptual mastery while accelerating students’ programming proficiency. The talk will conclude with reflections—grounded in the speaker’s educational research and practice in AI—on the role of MATLAB in cultivating talent for AI-related domains.

MATLAB & Simulink are widely used throughout the automotive software development lifecycle. Topics include an interpretation of the ASPICE process and its practice in detailed software design and unit testing; an in-depth explanation of model-based design; and a discussion of new talent demands in the AI era across algorithm modeling, systems engineering, automated testing, and cross-domain integration capabilities.

Explore the integration of MATLAB and LLMs. Users can easily call local or cloud-based foundation models to enable Q&A, code generation, model creation, and more. Build a knowledge base using existing resources and leverage retrieval-augmented generation to produce more accurate and personalized content. Combining generative AI with MATLAB supports every step—from writing and refining code to building complex engineering systems—opening up more possibilities for teaching.

Using your course as an example and drawing on the guest talks and MathWorks tools/resources, discuss the opportunities and challenges that the generative AI era brings to teaching reform. Choose one or more of the following topics to conduct a case study, develop a teaching-reform plan, and share discussion outcomes.
• Using generative AI to support teaching
• Offering AI general-education courses
• Adding AI technologies to traditional discipline teaching
• Aligning teaching content with industry needs

Distinguished Faculty Talk:
“Experience – Test – Innovate”: Building a Hardware-in-the-Loop Experimental Platform and Teaching Practice for Aerospace Programs (Shanghai Jiao Tong University, Xiaohui Zhang)
To address challenges in aerospace courses—broad knowledge scope, abstract content, and students’ difficulty in understanding—while also considering shifts in student interests under the widespread adoption of AI technologies, the teaching team leveraged multiple hardware-in-the-loop (HIL) simulation testbeds to build an experimental teaching system spanning different difficulty levels and tiers, including experiential/verification experiments, measurement/analysis experiments, and comprehensive innovation experiments. By making course content more visual and tangible, this approach effectively supports classroom teaching and improves students’ engagement and practical skills.

Industry Expert Talk:
Embedded Intelligence: An AI Trend Leading Engineering Education (MathWorks, Jason Wang)
We will take a deep dive into diverse applications of MATLAB in AI, covering the latest technical examples and case studies across computer vision, signal processing, and speech processing, and help build an efficient, systematic platform for engineering teaching and scientific research workflows.

Hands-on Workshop & Group Discussion:
Efficiently Generating MATLAB Applications with LLM Prompt Engineering: From Scripts to Interactive Apps (MathWorks, Yueyi Xu)
This hands-on session introduces how to efficiently generate, debug, and refactor MATLAB code using LLM through carefully designed prompts. The session starts with data visualization scripts, function refactoring, and error fixing, and gradually transitions to the automated creation of interactive MATLAB Apps. The session aims to help instructors master practical, end-to-end AI-assisted programming workflows that can be directly applied in teaching and research, ultimately improving productivity and efficiency.

• Low-cost Self-balancing Dual-rotor Modeling and Control: Model Predictive Control and Reinforcement Learning

This showcase presents a low-cost self-balancing dual-rotor system based on Arduino, demonstrating a complete engineering workflow from physical modeling and system identification to AI-enabled intelligent control design and hardware deployment. Designed for engineering education and project-based learning, it shows how a replicable, low-cost system can integrate modeling, advanced control, and AI control methods to realize closed-loop teaching practice from simulation to a physical prototype.

• LLM-based Intelligent Assistant

In this showcase, users can interactively chat with an LLM-based intelligent assistant in MATLAB and use voice to control a motor. Experience end-to-end support from MATLAB and Simulink for intelligent application design and development, including user interface design, Python model integration, large language model support, hardware control, deployment, and more.