NEW HANDS-ON Multimodal AI Essentials: Language, Vision, and Technical Use Cases
Instructor: Orange Gao, Shida Yu, and Nanqi Gong, Amazon
Level: Introductory
Duration: 4 hours
Course Time: 8:30 - 12:45
Benefits
This course enables the attendee to:
- Explain LLM and VLM fundamentals.
- Identify business problems suited to multimodal AI.
- Use pre-trained models for image and text analysis.
- Assess strengths and limits of current multimodal AI.
- Interpret model results for technical decisions.
- Create a simple technical application with multimodal AI.
Course Description
Unlock the power of artificial intelligence that understands both images and text—multimodal models are transforming how businesses extract insights and solve problems. This course provides a hands-on introduction to Large Language Models (LLMs) and Vision-Language Models (VLMs), with a focus on practical applications in business environments. Participants learn how leading organizations are using these advanced AI tools to streamline workflows, analyze multimedia data, and gain a competitive advantage. Through real-world examples and guided exercises, students will gain the skills to select, implement, and evaluate multimodal AI solutions—including creating simple prototypes—to address technical needs. No advanced coding experience required; this course is designed for curious professionals eager to leverage the next generation of artificial intelligence.
Intended Audience: technical experts, managers, analysts, and technical leads interested in leveraging artificial intelligence for real-world applications.
Orange (Zhao) Gao is an applied scientist at Amazon Lab126 in Cambridge, UK, specializing in multimodal AI, computer vision, and machine learning. She has led projects integrating vision-language models for robotics, smart devices, and AI-powered image analysis. Previously, she worked as a data scientist, developing machine learning and NLP solutions for business clients. Gao earned her PhD in Computer Science from Loughborough University in UK, focusing on deep learning for image reconstruction and augmented reality.
Shida Yu joined Amazon in March 2022 as a camera electrical engineer after receiving his MS in electrical engineering from the University of New South Wales. Throughout his tenure, he has delivered meaningful impact through innovative hardware designs and engineering solutions across many critical camera module projects for both Lab126 and Ring.
Nanqi Gong is currently with Amazon Asia Technology Center, working on camera technologies including freeform pixel sampling, Smart Desk AI robots, and event-based vision applications. She is also pursuing her MS in computer engineering at Columbia University and received her BS in computer engineering from the University of Hong Kong, where her research focuses on VR simulation systems, multimodal perception, and computer vision.