Anote AI Academy: Lecture 5 - Shafik Q скачать в хорошем качестве

Anote AI Academy: Lecture 5 - Shafik Q

Talk Title: Foundations & Architectures of Multi-Modal Machine Learning Talk Abstract: In this deep-dive session, Shafik will explore the fundamentals of multi-modal machine learning with a focus on the specific models and architectures that make it possible. The discussion will go beyond high-level concepts to give practical insight into how today's ubiquitous multimodal AI technologies (like image understanding, video generation, and cross-modal fusion techniques) actually work under the hood. If time allows, he’ll also touch on video understanding models and how they’re evolving alongside other multimodal systems. This session is designed for anyone who wants a stronger technical foundation in the models powering modern multimodal AI, whether you’re excited about computer vision, natural language + vision integration, or the next wave of generative and analytical capabilities. About Shafik: Shafik is a Senior Android-ML Games Engineer at The New York Times with a passion for machine learning, game development, and applied AI systems. He’s given talks at events like PyData NYC, AI4, and industry meetups on topics ranging from adversarial models and synthetic media to deep technical explorations of multimodal AI and computer vision. His work spans building intelligent ML products in both media and interactive systems, and he’s also published technical pieces on ML techniques in puzzles, handwriting recognition, and vision-language integration.