Foundations of Multimodal AI: Fusions, Architectures, & Beyond

Ever wondered how ML models and LLMs have evolved from classification models like BERT, to unimodal text-to-text like GPT-3.5, to now image/video generation, medical imaging (e.g., MRI, CT Scans, X-Rays), any-to-any, and even dolphin-to-audio models?

Join us at Data Engineering Pilipinas' Discord Channel on July 13, 8:00 PM to 9:30 PM (PHT/UTC+8), facilitated by Mr. Allan Tan, as we explore the convergence of NLP, Computer Vision, and Audio Signal Processing, among others.

We'll deep dive into the foundations of multimodality, covering everything from data fusions, architectures, datasets, training, evaluation, and beyond!

Hop on the DEP Discord channel to learn along!