https://github.com/tlesort/tlesort
https://github.com/tlesort/tlesort
Last synced: 5 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/tlesort/tlesort
- Owner: TLESORT
- Created: 2025-05-16T18:51:11.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-16T19:13:32.000Z (about 1 year ago)
- Last Synced: 2025-06-26T12:51:51.294Z (12 months ago)
- Size: 2.93 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Hi there 👋, I'm Timothée Lesort, a Senior Data Scientist at [Aignostics GmbH](https://www.aignostics.com/) in Berlin. My work focuses on training large-scale self-supervised vision models for histopathology (mostly tweaking Dinov2 training), aiming to improve cancer and rare disease diagnostics ( or at least the numbers in the benchmarks 🙃 ).
My expertise lies in deep learning for vision and language, with a strong interest in continual learning and representation learning for robust generalization and efficient scaling.
Previously, I conducted postdoctoral research at [UdeM](https://www.umontreal.ca/), [Mila – Quebec Artificial Intelligence Institute](https://mila.quebec/en/) under the supervision of [Irina Rish](https://mila.quebec/en/person/irina-rish/), where I worked on large-scale continual [pretraining of LLMs](https://arxiv.org/abs/2308.04014) (large language models).
I earned my PhD in Computer Science from [IP Paris - Institut Polytechnique de Paris](https://www.ip-paris.fr/en) (France) in the [U2IS lab](http://u2is.ensta-paris.fr/) under the supervision of [David Filliat](https://www.researchgate.net/profile/David-Filliat). My doctoral research, titled "[Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes](https://arxiv.org/abs/2007.00487)," investigated the use of replay mechanisms, particularly generative models, for continual learning. I also explored replay for continual reinforcement learning and the theoretical limitations of regularizing dynamic architectures in continual learning. I hold a Master's degree in Electronics and Robotics from CPE Lyon.
I love train 🚞 and bike 🚲 travelling, big trees 🌳 and playing chess ♟
**Featured Research Projects:**
* [Pretraining of Vision Transformers for Histopathology](https://arxiv.org/pdf/2501.05409)
* [Continual pre-training of large language models.](https://arxiv.org/abs/2308.04014)
* [Characterization of data distribution drifts.](https://arxiv.org/abs/2104.01678)
* [A better understanding of continual learning models.](https://arxiv.org/abs/2106.01834)
* [The impact of large pre-trained models for continual learning.](https://arxiv.org/abs/1912.03049)
* [Continuum](https://github.com/Continvvm/continuum): A PyTorch-based library designed to facilitate continual learning experimentation through diverse benchmarks, aiming to accelerate progress in the field.
* [continual\_learning\_papers](https://github.com/optimass/continual_learning_papers): A curated catalogue of continual learning papers
[Google Scholar](https://scholar.google.com/citations?user=5NttkuoAAAAJ&hl=en)
[LinkedIn](https://linkedin.com/in/timoth%C3%A9e-lesort-128039aa)
[Research Gate](https://www.researchgate.net/profile/Timothee-Lesort)
[Semantic Scholar](https://www.semanticscholar.org/author/Timoth%C3%A9e-Lesort/26418330)
[Twitter](https://twitter.com/tlesort)