Master Generative AI -
From Curiosity to Creation
VIZA 489 501, VIZA 689 601
Explore cutting-edge research in generative artificial intelligence, from foundational neural networks to large language models and beyond for all backgrounds.
Enroll Now
Course Introduction Video
Generative AI
Generative AI is a subset of artificial intelligence that uses machine learning models to create new, original content by learning statistical patterns and relationships from large datasets during training.
The core mechanism involves learning the underlying probability distributions of the training data, enabling the model to sample from these learned distributions to generate new content that maintains the statistical properties and patterns of the original dataset.
Why does Generative AI matter?
It democratizes creativity and productivity by enabling anyone to generate professional-quality content, automate complex tasks, and rapidly prototype ideas without specialized technical skills.
How does Generative AI work?
It uses deep learning models and neural networks to analyze patterns in training data, then applies these learned patterns to generate new, original content based on user prompts or inputs.
Applications
Generative AI is transforming how we create, design, and interact with digital content. From producing lifelike images, videos, and 3D models to generating music, text, and immersive virtual experiences, it empowers new forms of creativity and innovation across industries. In education and entertainment, it enables personalized learning and storytelling; and in engineering and design, it accelerates prototyping and visualization. By blending human imagination with machine intelligence, generative AI opens possibilities for more efficient workflows, novel user experiences, and solutions to complex real-world problems.
Course Modules
Module 1
Module 2
Module 3
Module 4
Module 5
Weeks 1-2
Foundations of Generative AI
Topics
Introduction to Generative AI and it’s applications
Visual representation basics
Image processing fundamentals
Handouts
Generative AI Model
AI Ethics & guidelines
Popular AI Research
Biases & AI Ethics
Course Information
Syllabus
Last updated Aug’25
Schedule
TBD
Fall 2025
credits
3 credits
VIZA 489 501,
VIZA 689 601
format
in-Person
Room ARC C 303
Meet your instructor
Prof. Dr. Suryansh Kumar
Suryansh Kumar is an Assistant Professor of Visual Computing and Computational Media at Texas A&M University. He also holds appointments in the Electrical and Computer Engineering Department and Computer Science Department at TAMU. Dr. Kumar directs the Visual and Spatial AI Lab within the College of PVFA where his group conducts research in the field of 3D computer vision, AI, and robotic automation.
Before joining Texas A&M University, Dr. Kumar worked at ETH Zürich. Disney Research honored him with the Best Algorithm Award at CVPR 2017 for his work on non-rigid 3D acquisition for marker-less motion capture, and his Ph.D. thesis was nominated for the J. G. Crawford Prize at ANU for Best Interdisciplinary Ph.D. Thesis in 2019. His current research focuses on designing next-generation visual and spatial intelligence systems.
LAAH 202
Generative AI
We solve real-world visual automation problems by leveraging artificial intelligence for visual representation and decision-making tasks.
Course
Projects
Support
Office Hours
2025 Visual & Spatial Lab. All Rights Reserved