| CARVIEW |
Jose Javier Gonzalez Ortiz
- Research Scientist, DataBricks
- josejg mit.edu
I got my PhD in Computer Science at MIT CSAIL working with John Guttag and Adrian Dalca. During my PhD I worked in efficient deep learning methods, and for my thesis I focused on learning reconfigurable vision models, where multiple tasks are learned jointly in an amortized way. We achieved this using techniques such as hypernetworks and in-context learning. During my PhD I also worked on asynchronous large-scale distributed training and neural network pruning methods.
While at MIT, I co-organized Missing Semester, a lecture series on programmer tools often left untaught in modern CS curriculums. During my PhD, I interned at Facebook AI Research and Microsoft Research. Previously, I received a BSc in Telematics Engineering from ICAI in Spain, and interned at CERN Openlab.
Deep Learning Libraries
-
🧬
UniverSeg – Universal Medical Image Segmentation Models
-
🌿
ShrinkBench – Neural Network Pruning Framework
-
🔥
HyperLight – Hypernetworks in Pytorch made easy
-
âš¡
ThunderPack – Blazingly fast multi-modal data format
-
🚀
Pylot – Experiment management for deep learning science
Publications
MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance
Hallee Wong, Jose Javier Gonzalez Ortiz, John Guttag, Adrian V. Dalca International Conference on Computer Vision - ICCV 2025. [paper] [code] [website]LoRA Learns Less and Forgets Less
Dan Biderman, Jose Javier Gonzalez Ortiz, Jacob Portes, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, Cody Blakeney, John P. Cunningham Transactions on Machine Learning Research (TMLR) 2024, Featured Certification. [paper] [code] [website]Introducing DBRX: A New State-of-the-Art Open LLM
The Mosaic Research Team Mosaic Research Blog. [blog] [code]Tyche: Stochastic In-Context Learning for Universal Medical Image Segmentation
Marianne Rakic, Hallee Wong, Jose Javier Gonzalez Ortiz, Beth Cimini, John Guttag, Adrian V. Dalca Computer Vision and Pattern Recognition Conference - CVPR 2024 (Highlight). [paper] [code] [website]Magnitude Invariant Parametrizations Improve Hypernetwork Learning
Jose Javier Gonzalez Ortiz, John Guttag, Adrian V. Dalca International Conference on Learning Representations - ICLR 2024. [paper] [code]Scale-Space Hypernetworks for Efficient Biomedical Imaging
Jose Javier Gonzalez Ortiz, John Guttag, Adrian V. Dalca NeurIPS 2023. [paper] [code]Universeg: Universal Medical Image Segmentation
Jose Javier Gonzalez Ortiz*, Victor Butoi*, Tianyu Ma, Mert Sabuncu, John Guttag, Adrian V. Dalca International Conference on Computer Vision - ICCV 2023. [paper] [code] [website]Trade-offs of Local SGD at Scale: An Empirical Study
Jose Javier Gonzalez Ortiz, Jonathan Frankle, Mike Rabbat, Ari Morcos, Nicolas Ballas NeurIPS 2020 OptML Workshop. [paper] [code] [poster]What is the State of Neural Network Pruning?
Jose Javier Gonzalez Ortiz*, Davis Blalock*, Jonathan Frankle, John Guttag MLSys 2020, Oral. [paper] [code] [slides] [poster]Standardizing Evaluation of Neural Network Pruning
Jose Javier Gonzalez Ortiz, Davis Blalock, John Guttag SOSP 2019 AI Systems Workshop, Oral. [paper] [code] [slides] [poster]Learning from Few Subjects with Large Amounts of Voice Monitoring Data
Jose Javier Gonzalez Ortiz, Daryush Mehta, Jarrad Van Stan, Robert Hillman, John Guttag, Marzyeh Ghassemi MLHC 2019, Oral. [paper] [slides] [poster]Image Segmentation of Liver Stage Malaria Infection
Ava Soleimany, Harini Suresh, Jose Javier Gonzalez Ortiz, Divya Shanmugam, Nil Gural, John Guttag, Sangeeta Bhatia ICML 2019 Workshop on Computational Biology. [paper]Heart Sound Classification based on Temporal Alignment Techniques
Jose Javier Gonzalez, Cheng Perng Phoo, Jenna Wiens CinC 2016. [paper] [poster]A Simple Power Attack in the TwoFish Key Schedule
Jose Javier Gonzalez Ortiz, Kevin J. Compton Bachelor Thesis 2016. [paper] [code] [slides]
Projects
- Missing Semester
– The Missing Semester of Your CS Education
- dotfiles
– Personal configuration files
- The End of Signature – Artpiece
– AI driven signature sculpture at Kendall Square
- MIT Intro to Deep Learning
– Crash course on Deep Learning techniques
- Advent of Code
– My solutions to the festive programming challenges
- LED Cube 8x8x8
– I designed, built and coded a 3D LED cube
- DTWpy
– Fast and parallel computation of Dynamic Time Warping in Python
Awards & Honors
Qualcomm Innovation Fellowship 2018
la Caixa Foundation Fellowship 2018
Undergraduate Excellence Award – U.P.Comillas ICAI 2016
Excellence Scholarship for County of Madrid 2012-2016