Transforming Computer Vision with LLMs - Key Projects and Insights

Explore the revolutionary impact of large language models (LLMs) on computer vision in this 44-minute talk. Gain insights into how text-only LLMs are achieving remarkable success in visual understanding through prompting and tool use. Discover key LLM-centered projects transforming the field, including VisProg, ViperGPT, VoxelGPT, and HuggingGPT. Learn about the challenges and lessons from building VoxelGPT, and acquire practitioner's insights into domain-specific prompt engineering. Delve into the future prospects of LLMs in computer vision. Suitable for researchers and practitioners interested in computer vision, generative AI, LLMs, and machine learning.

Transforming Computer Vision with LLMs