Extra-Seminar, Docentship Lecture: Introduction to Large Language Models in Image Analysis: Theory and Applications – Ekta Vats
- Date: 6 May 2024, 11:00–12:00
- Location: Theatrum Visuale, room 100155, building 10, Ångström Laboratory
- Type: Seminar
- Lecturer: Ekta Vats
- Organiser: Centre for Image Analysis
- Contact person: Natasa Sladoje
Large Language Models (LLMs) have revolutionized natural language processing, but their potential extends far beyond text understanding. This lecture delves into integrating LLMs with images, exploring their theory and practical applications. We will explore the convergence of language and images, establish foundational knowledge in LLMs, and understand how LLMs and its variants can enhance various image analysis and computer vision tasks, such as OCR/HTR, image captioning, visual question answering, image generation, and beyond. The ethical considerations and potential biases inherent in deploying LLMs for vision tasks will be discussed, providing insights into their individual capabilities and limitations.