Exploring the frontier where language meets vision in artificial intelligence. We host and archive presentations from leading researchers and practitioners in multimodal AI, visual reasoning, and language-guided perception. Founded in 2020 as Computer Vision Talks, we’ve evolved to reflect the exciting convergence of language and vision technologies that are defining the next generation of AI systems.

Our mission is to foster knowledge exchange, inspire collaboration, and accelerate innovation at this critical intersection of disciplines.
Join our community of researchers, engineers, students, and enthusiasts passionate about building machines that can both see and understand the world through language.