Nicholas Carolan

Github / Google Scholar / LinkedIn / Twitter / Substack

I'm an engineer and researcher working on machine intelligence.

My interests lie in building and understanding models that can solve fundamental problems. I currently train machine learning models at Google.

Previously, I worked on computer vision and computational photography, where I contributed to research on "rich human feedback" for generative models that won a CVPR best paper award. I studied computer science at Amherst College.

Recent News

June 19, 2024: Our paper wins the best paper award at CVPR!
April 4, 2024: Rich Human Feedback for Text-to-Image Generation is selected as an oral presentation at CVPR.
February 26, 2024: Our paper Rich Human Feedback for Text-to-Image Generation is accepted to CVPR.

Publications

Rich Human Feedback for Text-to-Image Generation. Youwei Liang*, Junfeng He*, Gang Li*, Peizhao Li, Arseniy Klimovskiy, Nicholas Carolan, Jiao Sun, Jordi Pont-Tuset, Sarah Young, Feng Yang, Junjie Ke, Krishnamurthy Dj Dvijotham, Katie Collins, Yiwen Luo, Yang Li, Kai J Kohlhoff, Deepak Ramachandran, Vidhya Navalpakkam. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
[ArXiv] [Blog]

• Winner of best paper award, oral presentation.

Projects

COS302

• Self-studied Princeton's COS 302 (Mathematics for Machine Learning) using publicly available lectures and materials. Repository contains all my problem sets and programming assignments.

Miscellaneous

These Places Do Not Exist

• Fake census tracts for NeurIPS 2021 Workshop on ML for Creativity and Design.