avatar

Linh Tran (she/her)

Email | CV | Google Scholar | Twitter

I am a Senior Research Scientist at Autodesk AI lab and a PhD student at the Imperial College London under the supervision of Maja Pantic. Before joining Autodesk, I was a research intern at Google Brain and Samsung AI.

I am generally interested in learning with limited supervision, deep generative modeling, representation learning, and its application to 2D and 3D vision. My research focuses on learning interpretable and human-controllable representations using deep probabilistic modeling. In particular, I am interested in learning representations with limited supervision that generalizes to unseen environments and across tasks. I am excited by applying these methods to 2D and 3D computer vision, fairness, and robotics (vision-based, Sim-to-Real transfer) in which large-scale data is available, however, annotations are scarce. I am also interested in sequential data modeling, approximate inference, and model distillation.

Please contact me if you are interested to collaborate. The Autodesk AI lab has internship positions open every summer.

News

Neurips 2021 Outstanding Reviewer Award (8%)

I am very grateful (and proud!) to have received Outstanding Reviewer Award from NeurIPS this year.

Internship at the AI lab for 2022 (summer)

Our team (Autodesk AI lab) is looking for interns for the summer of 2022. You can apply following this link via myworkdayjobs. Feel free to reach out to me if you want to chat and know more!

Women in Machine Learning (WiML) Workshop @ NeurIPS 2021

I am super excited to be in the organizing committee of the WiML Workshop at NeurIPS this year. I will be one of the finance and sponsorship co-chair.

Publications

Pre-prints

pubavatar
Group-disentangled Representation Learning with Weakly-Supervised Regularization
L. Tran, A.H. Khasahmadi, A. Sanghi and S. Asgari
arXiv preprint arXiv:2110.12185, 2021
[ arxiv ]
pubavatar
Cauchy-Schwarz Regularized Autoencoder
L. Tran, M. Pantic and M.P. Deisenroth
arXiv preprint arXiv:2101.02149, 2021
[ arxiv | github ]

Conference articles

pubavatar
How Good is the Bayes Posterior in Deep Neural Networks Really?
F. Wenzel*, K. Roth*, B.S. Veeling*, J. Swiatkowski, Tran, L., S. Mandt, J. Snoek, T. Salimans, R. Jenatton and S. Nowozin (* denotes equal contribution)
37th International Conference on Machine Learning (ICML), 2020
[ arxiv | icml proceedings | github ]
pubavatar
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
J. Swiatkowski, K. Roth, B.S. Veeling, L. Tran, J.V. Dillon, S. Mandt, J. Snoek, T. Salimans, R. Jenatton and S. Nowozin
37th International Conference on Machine Learning (ICML), 2020
[ arxiv | icml proceedings ]
pubavatar
GAGAN: Geometry-Aware Generative Adversarial networks
J. Kossaifi, L. Tran, Y. Panagakis and M. Pantic
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[ arxiv | cvpr proceedings ]
pubavatar
Deepcoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding.
D. L. Tran*, R. Walecki*, Ognjen (Oggi) Rudovic*, S. Eleftheriadis, B. Schüller and M. Pantic (* denotes equal contribution)
Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017
[ arxiv | iccv proceedings | poster ]

Journal articles

pubavatar
Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks
L. Tran, J. Kossaifi, Y. Panagakis and M. Pantic
International Journal of Computer Vision, pp.1-21, 2019.
[ ijcv open access ]
pubavatar
ProfPPIdb: pairs of physical protein-protein interactions predicted for entire proteomes
L. Tran, T. Hamp and B. Rost
Plos ONE, 2018
[ bioarxiv | plos one open access | project page ]

Peer-reviewed workshop articles

pubavatar
Weakly-Supervised Group Disentanglement using Total Correlation
L. Tran, S.A. Taghanaki, A.H. Khasahmadi, A. Sanghi
Workshop on Weakly Supervised Learning (WeaSuL), ICLR 2021
[ workshop page | workshop paper ]
pubavatar
Hydra: Preserving Ensemble Diversity for Model Distillation
L. Tran, B.S. Veeling, K. Roth, J. Swiatkowski, J.V. Dillon, J. Snoek, S. Mandt, T. Salimans, S. Nowozin and R. Jenatton
Uncertainty & Robustness in Deep Learning (UDL), ICML 2020
[ arxiv (long version) | workshop page | workshop paper ]