Arpit Bansal

I am a Research Scientist at Google, where I work on text+image-to-image tasks and vision encoders. Prior to joining Google, I earned my PhD in Computer Science from the University of Maryland, College Park, advised by Professor Tom Goldstein. I am particularly interested in a range of multi-modal vision tasks, including text-to-image generation, image editing, and image reasoning. My work in these areas employs both diffusion and autoregressive methods to tackle various challenges in image processing. Additionally, with the aim to build neural networks that can do logical extrapolation and learn problem-solving skills, I have built neural-networks that can learn algorithms and thus extrapolate from easy-to-hard tasks using recurrence. A complementary aspect of my research includes investigating the inherent behaviors and characteristics of neural networks in various scenarios. Prior to UMD, I received my Bachelors and Masters (Dual Degree) from IIT Kharagpur in Electrical Engineering. My CV is available here.

Along with research, I enjoy playing keyboard, and hiking.