Nilesh Arnaiya
Hi there. I am currently a Masters student at the University of Witwatersrand, South Africa. Before starting my masters, I was an android developer with a Tiktok like Indian startup. I started my AI journey with Udacity’s AI course and since then I’ve been on and off and have finally figured that I want to learn about the mind and make robots do cool stuff. My research interests are within the realm of Computer science and reinforcement learning for robotics. I’m currently at the - RAIL LAB.
I’m a big potterhead and when I’m not doing all the above, I’m enjoying life with mentoring people at Mentorcruise or books, movies, yoga, ngos and exploration of apps. I also blog - Blog
Send me an owl - @nilesharnaiya@gmail.com
Session
Recently, most works focus on synthesizing independent images; While for
real-world applications, it is common and necessary to generate a series of coherent images for story-telling. In this work, we mainly focus on story visualization and continuation tasks and propose AR-LDM, a latent diffusion model auto-regressively conditioned on history captions and generated images. To my best knowledge, this is the first work successfully leveraging diffusion models for coherent visual story synthesizing.