Jasmine Collins

Currently I am a Research Scientist at Databricks.

Before that, I had the pleasure of doing my PhD student at UC Berkeley with Jitendra Malik, funded by the NSF GRFP. I have done insternships at Meta and Amazon Science, and was part of the inaugural group of AI Residents at Google Brain.

email  /  google scholar  /  twitter  /  github

profile photo
Research

My research has primarily focused on computer vision and cognitive science. In general, I’m interested in making machine learning model outputs more aligned with human preferences and behavior. I'm also interested in problems such as learning with fewer human-labeled annotations, improving sample efficiency, and building more robust models.

Computer Vision & Deep Learning

catnet
CA2T-Net: Category-Agnostic 3D Articulation Transfer from Single Image
Jasmine Collins, Anqi Liang, Jitendra Malik, Hao Zhang, Frederic Devernay
arXiv, 2023
paper
ganmouflage
GANmouflage: 3D Object Nondetection with Texture Fields
Rui Guo, Jasmine Collins, Oscar de Lima, Andrew Owens
Computer Vision and Pattern Recognition (CVPR), 2023
paper / project page
abo
ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
Jasmine Collins, Shubham Goel, Kenan Deng, Achleshwar Luthra, Leon Xu, Erhan Gundogdu, Xi Zhang, Thomas F. Yago Vicente, Thomas Dideriksen, Himanshu Arora, Matthieu Guillaumin, Jitendra Malik
Computer Vision and Pattern Recognition (CVPR), 2022
paper / project page
sloss
Accelerating Training of Deep Neural Networks with a Standardization Loss
Jasmine Collins, Johannes Balle, Jonathon Shlens
Women in Machine Learning Workshop, 2019
paper
cap_n_train
Capacity and Trainability in Recurrent Neural Networks
Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo
International Conference on Learning Representations (ICLR), 2017
paper / project page

Cognitive Science & Computational Neuroscience

obj-comp
Three-Dimensional Object Completion in Humans and Computational Models
Eunice Yiu, Jasmine Collins, Alison Gopnik
Cognitive Science Society (CogSci), 2022 (Oral Presentation)
paper
blickets
Learning Causal Overhypotheses through Exploration in Children and Computational Models
Eliza Kosoy*, Adrian Liu*, Jasmine Collins, David M Chan, Jessica B. Hamrick, Nan Rosemary Ke, Sandy Huang, Bryanna Kaufmann, John Canny, Alison Gopnik
Conference on Causal Learning and Reasoning (CLeaR), 2022 (Oral Presentation)
paper
kids
Exploring Exploration: Comparing Children with RL Agents in Unified Environments
Eliza Kosoy, Jasmine Collins, David M Chan, Sandy Huang, Deepak Pathak, Pulkit Agarwal, John Canny, Alison Gopnik, Jessica B. Hamrick
International Conference on Learning Representations (ICLR) Workshop, 2020
(Oral Presentation)
paper / blog post
birds
Automatically Inferring Task Context for Continual Learning
Jasmine Collins, Kelvin Xu, Bruno Olshausen, Brian Cheung
Cognitive Computational Neuroscience (CCN), 2019   (Oral Presentation)
paper / talk (recording)
nmeth
Inferring Single-trial Neural Population Dynamics Using Sequential Auto-encoders
Chethan Pandarinath, Daniel J O'Shea, Jasmine Collins, Rafal Jozefowicz, Sergey D. Stavisky, Jonathan C. Kao, Eric M. Trautmann, Matthew T. Kaufman, Stephen I. Ryu, Leigh R. Hochberg, Jaimie M. Henderson, Krishna V. Shenoy, Larry F. Abbott, David Sussillo
Nature Methods, 2018
paper / code

Teaching
cs188 Graduate Student Instructor, CS 188 Spring 2022

Graduate Student Instructor, CS 188 Spring 2020

Thanks to Jon Barron for this iconic website template.