11-day longest streak
Jonathan Lorraine I'm a research scientist at NVIDIA in the Spatial Intelligence Lab with Sanja Fidler, working on generative physical AI. I did my PhD in machine learning at the…
Jonathan Lorraine
I'm a research scientist at NVIDIA in the Spatial Intelligence Lab with Sanja Fidler, working on generative physical AI. I did my PhD in machine learning at the University of Toronto, advised by David Duvenaud. My research centers on ultra-scalable nested optimization - building the tools that power modern AI models, and using them for things like multimodal generation, hyperparameter tuning, and learning in games. Before NVIDIA, I worked on production AutoML at Google and on multi-agent learning at Facebook (Meta) AI Research with Jakob Foerster.
jonlorraine.com · Google Scholar · LinkedIn · @jonLorraine9
Selected work
- OmniDreams - a real-time generative world model for closed-loop autonomous vehicle simulation
- MOTIVE (Oral, ICML 2026) - motion attribution for video generation
- LLaMA-Mesh - unifying 3D mesh generation with language models
- LATTE3D (ECCV 2024) / ATT3D (ICCV 2023) - fast, amortized text-to-3D
- Optimizing Millions of Hyperparameters by Implicit Differentiation (AISTATS 2020)
- Self-Tuning Networks (ICLR 2019) - bilevel optimization of hyperparameters
Research interests
Generative models · bilevel and hyperparameter optimization · meta-learning · multi-agent learning · efficient and multi-fidelity optimization-
hypernet-hypertraining ★ PINNED
Code for Stochastic Hyperparameter Optimization through Hypernetworks
TeX ★ 29 8y agoExplain → -
csc411_fall2018_tutorials
A collection tutorial materials for the Fall 2018 CSC411/CSC2515 (Introduction to Machine Learning) at the University of Toronto.
Jupyter Notebook ★ 16 9d agoExplain → -
STN-code ⑂
Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088
Python ★ 4 9d agoExplain → -
LLM-HPO-code ⑂
Using Large Language Models for Hyperparameter Optimization
Jupyter Notebook ★ 4 9d agoExplain → -
TDA-code ⑂
Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
★ 4 1y agoExplain → -
LLaMA-Mesh-code ⑂
Unifying 3D Mesh Generation with Language Models
★ 4 1y agoExplain → -
Forecasting-Model-Search-code ⑂
A system for automating selection and optimization of pre-trained models from the TAO Model Zoo
★ 4 2y agoExplain → -
GMN-code ⑂
Graph Metanetworks for Processing Diverse Neural Architectures (ICLR 2024 spotlight)
★ 4 1y agoExplain → -
lorraine2
Jonathan Lorraine
★ 2 9d agoExplain → -
advisory-database ⑂
Security vulnerability database inclusive of CVEs and GitHub originated security advisories from the world of open source software.
★ 0 9d agoExplain →
No repos match these filters.