AI & Fundamentals

Recent Development of Generative AI Focused on Computer Vision - Dongjun Kim, Postdoctoral Scholar, Stanford University

Abstract:

With the recent advancements in diffusion models, the image generation problem has become nearly resolved in terms of quality. However, because most large language models (LLMs) are built on autoregressive transformer architectures, there remains a significant gap between LLMs and diffusion models, and it is challenging to combine text generation and image/video/audio generation in a single unified model. This talk will explore recent efforts to bridge this gap.