I am a PhD student at Harvard University, advised by Prof. Todd Zickler. I also work closely with Prof. Ko Nishino and have spent two wonderful summers in Kyoto.
Previously, I graduated from the University of Pennsylvania majoring in Mathematics and Computer Science. During my undergrad, I was fortunate to work with Prof. Jianbo Shi and Prof. Dan Roth.
Research
My current research interests include computer vision, generative models and multi-modal learning.
Specifically, I enjoy building models that combine learning based approach with physics intuition and inspirations from the human visual system. I’m also interested in the intersection of vision with language and art.
Selected Publications
Xinran Nicole Han, Todd Zickler, Ko Nishino
Advances in Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)
TL;DR: We present a bottom-up, patch-based diffusion model for monocular shape from shading that produces multimodal outputs, similar to multistable perception in humans.
Paper | Project | Code
Zhou Fan, Xinran Han, Zi Wang
Transactions on Machine Learning Research (TMLR), February 2024
Paper
Xinran Han, Todd Zickler
Proceedings of the NeurIPS Workshop on Symmetry and Geometry in Neural Representations, PMLR 228, 2023
TL;DR: We present a neural model for inferring a curvature field from shading images that is invariant under lighting and texture variations, drawing on perceptual insights and mathematical derivations.
Paper
Soham Dan*, Xinran Han*, Dan Roth (* equal contribution)
Findings of EMNLP, 2021.
Paper
Miscellaneous
Outside of research, I enjoy visiting art museums, watching movies and reading about philosophy and psychology.