Join us for this edition of the Research Paper Reading Series as we dive into "Vision Language Models: A Survey of 26K Papers (CVPR, ICLR, NeurIPS 2023–2025)", a comprehensive survey that maps the rapidly evolving landscape of Vision Language Models (VLMs).
From image understanding and multimodal reasoning to emerging agentic capabilities, this paper explores how VLMs are reshaping the future of AI by bridging visual and textual intelligence. Together, we'll unpack key trends, architectures, benchmarks, and research directions that have emerged from thousands of papers across top AI conferences.
Whether you're a beginner looking to understand multimodal AI or an enthusiast eager to keep up with the latest research, this session offers a structured and accessible way to navigate one of the most exciting areas in machine learning today.
Come curious, leave with a clearer picture of where AI is headed—and the research driving it forward.
Speaker: Abhay Yadav
Date: 19 June 2026
Time: 6:00 PM IST
Platform: Discord – AI Durg
