I am an Indian national, born an brought up in Kolkata, often referred to as the City of Joy. I finished my secondary & higher-secondary schooling in my hometown. I then appeared in WBJEE, a competitive exam for undergraduate studies. I secured a rank of approx. 3k and got admitted in Institute of Engineering & Management with a concentration on Electronics & Communication Engineering. While an undergrad, I got interested in the field of Computer Vision and Machine Learning and joined Indian Statistical Institute (ISI), Kolkata around 2014 as an intern and worked on several projects with two academics and published 6 papers within 3 years. I then went on to pursue Masters at Indian Institute of Technology (IIT), Kharagpur where I worked on a Deep Medical Imaging project sponsored by Intel India Pvt. Ltd. I, did not however, finish my masters. I dropped out and moved to UK (around Oct. 2019) to join a Ph.D program (with full funding) at SketchX lab, University of Surrey. During my PhD, I worked on the intersection of Computer Vision, Graphics and Deep Learning under the supervision of Dr. Yi-Zhe Song and others. As of March ‘23, I joined the Deep Learning team of MediaTek Research, Cambridge as a full-time Deep Learning research scientist. My broad focus is both theoretical and applied research in Diffusion Models for computer vision. Before that, I have worked as an intern with the same team for nearly 10 months. I am expected to graduate around early-2024. In my Ph.D tenure till date, I have published in top conferences like NeurIPS, ICML, ICLR, CVPR, SIGGRAPH and more. I was also recently recognized as a top reviewer at NeurIPS ‘23. More details can be found in my CV below.