Follow
James Lucas
James Lucas
Research Scientist, NVIDIA
Verified email at cs.toronto.edu - Homepage
Title
Cited by
Cited by
Year
Lookahead optimizer: k steps forward, 1 step back
M Zhang, J Lucas, J Ba, GE Hinton
Advances in neural information processing systems 32, 2019
8352019
Sorting out Lipschitz function approximation
C Anil, J Lucas, R Grosse
International Conference on Machine Learning, 291-301, 2019
3782019
Don't blame the ELBO! A linear VAE perspective on posterior collapse
J Lucas, G Tucker, R Grosse, M Norouzi
arXiv preprint arXiv:1911.02469, 2019
349*2019
Preventing gradient attenuation in lipschitz constrained convolutional networks
Q Li, S Haque, C Anil, J Lucas, RB Grosse, JH Jacobsen
Advances in neural information processing systems 32, 2019
1122019
Aggregated momentum: Stability through passive damping
J Lucas, S Sun, R Zemel, R Grosse
arXiv preprint arXiv:1804.00325, 2018
852018
Adversarial distillation of bayesian neural network posteriors
KC Wang, P Vicol, J Lucas, L Gu, R Grosse, R Zemel
International conference on machine learning, 5190-5199, 2018
782018
Att3d: Amortized text-to-3d object synthesis
J Lorraine, K Xie, X Zeng, CH Lin, T Takikawa, N Sharp, TY Lin, MY Liu, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
652023
Regularized linear autoencoders recover the principal components, eventually
X Bao, J Lucas, S Sachdeva, RB Grosse
Advances in Neural Information Processing Systems 33, 6971-6981, 2020
452020
Analyzing monotonic linear interpolation in neural network loss landscapes
J Lucas, J Bae, MR Zhang, S Fort, R Zemel, R Grosse
arXiv preprint arXiv:2104.11044, 2021
34*2021
Optimizing data collection for machine learning
R Mahmood, J Lucas, JM Alvarez, S Fidler, M Law
Advances in Neural Information Processing Systems 35, 29915-29928, 2022
272022
How much more data do i need? estimating requirements for downstream tasks
R Mahmood, J Lucas, D Acuna, D Li, J Philion, JM Alvarez, Z Yu, S Fidler, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
272022
Graph metanetworks for processing diverse neural architectures
D Lim, H Maron, MT Law, J Lorraine, J Lucas
arXiv preprint arXiv:2312.04501, 2023
212023
Latte3d: Large-scale amortized text-to-enhanced3d synthesis
K Xie, J Lorraine, T Cao, J Gao, J Lucas, A Torralba, S Fidler, X Zeng
arXiv preprint arXiv:2403.15385, 2024
192024
The calibration generalization gap
AM Carrell, N Mallinar, J Lucas, P Nakkiran
arXiv preprint arXiv:2210.01964, 2022
172022
Theoretical bounds on estimation error for meta-learning
J Lucas, M Ren, I Kameni, T Pitassi, R Zemel
arXiv preprint arXiv:2010.07140, 2020
152020
Few-Shot Attribute Learning
M Ren, E Triantafillou, KC Wang, J Lucas, J Snell, X Pitkow, AS Tolias, ...
13*2020
Causal Scene BERT: Improving object detection by searching for challenging groups of data
C Resnick, O Litany, A Kar, K Kreis, J Lucas, K Cho, S Fidler
arXiv preprint arXiv:2202.03651, 2022
8*2022
Bridging the sim2real gap with care: Supervised detection adaptation with conditional alignment and reweighting
V Prabhu, D Acuna, A Liao, R Mahmood, MT Law, J Hoffman, S Fidler, ...
arXiv preprint arXiv:2302.04832, 2023
72023
Interactive AI Material Generation and Editing in NVIDIA Omniverse
H Abu Alhaija, J Lucas, A Zook, M Babcock, D Tyner, R Rao, M Shugrina
ACM SIGGRAPH 2023 Real-Time Live!, 1-2, 2023
22023
Improving hyperparameter optimization with checkpointed model weights
N Mehta, J Lorraine, S Masson, R Arunachalam, ZP Bhat, J Lucas, ...
arXiv preprint arXiv:2406.18630, 2024
12024
The system can't perform the operation now. Try again later.
Articles 1–20