About Event

This workshop provides a technical exploration of advanced Multimodal AI architectures, focusing on the fusion and processing of text, vision, speech, audio, and video modalities within intelligent systems. Participants will examine Vision-Language Models (VLMs), Large Multimodal Models (LMMs), embeddings, multimodal representation learning, attention mechanisms, RAG pipelines, prompt engineering, and model inference workflows. Through hands-on demonstrations and implementation-oriented sessions, participants will work with modern AI frameworks and tools to understand multimodal data pipelines, model integration, fine-tuning, and deployment for research and industry applications.

Who Can Attend?
Undergraduate and postgraduate students of any domain
Research scholars and Ph.D. candidates
Faculty members and academic professionals
AI, Machine Learning, and Data Science enthusiasts
Software developers and IT professionals
Industry practitioners interested in Generative AI and Multimodal AI
Professionals seeking to upskill in emerging AI technologies