Jasmine Collins

I am a PhD student at UC Berkeley and a member of Berkeley AI Research advised by Jitendra Malik and funded by the NSF GRFP. Previously I was part of the inaugural group of AI Residents at Google Brain.

I did my undergraduate at the University of Pittsburgh where I double-majored in neuroscience and computer science, and minored in chemistry. During my time there I had the pleasure of working with David Koes on computational drug discovery.

email / CV / google scholar / twitter / github

Research

My current research interests include computer vision and human perception. I'm interested in how we can teach computers to see and perceive the world as a collection of objects in 3D without requiring hundreds of thousands of annotations. Plus, how can computational tools be used in novel ways to help us better understand and uncover insights about human perception?

	ABO: Dataset and Benchmarks for Real-World 3D Object Understanding Jasmine Collins, Shubham Goel, Achleshwar Luthra, Leon Xu, Kenan Deng, Xi Zhang, Thomas F. Yago Vicente, Himanshu Arora, Thomas Dideriksen, Matthieu Guillaumin, Jitendra Malik arXiv, 2021 paper / bibtex / website
	GANmouflage: 3D Object Nondetection with Texture Fields Rui Guo, Jasmine Collins, Oscar de Lima, Andrew Owens arXiv, 2021 paper / bibtex / website
	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 / bibtex
	Automatically Inferring Task Context for Continual Learning Jasmine Collins, Kelvin Xu, Bruno Olshausen, Brian Cheung Cognitive Computational Neuroscience (CCN), 2019 (Oral Presentation) paper / bibtex / talk (recording)
	Accelerating Training of Deep Neural Networks with a Standardization Loss Jasmine Collins, Johannes Balle, Jonathon Shlens arXiv, 2019 paper / bibtex
	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 / bibtex / code
	Capacity and Trainability in Recurrent Neural Networks Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo International Conference on Learning Representations (ICLR), 2017 paper / bibtex / data
	A D3R Prospective Evaluation of Machine Learning for Protein-ligand Scoring Jocelyn Sunseri, Matthew Ragoza, Jasmine Collins, David Koes Journal of Computer-Aided Molecular Design, 2016 paper / bibtex

Teaching

Graduate Student Instructor, CS 188 Spring 2020

Thanks to Jon Barron for this iconic website template.