Paul Janson

According to our database, Paul Janson authored at least 10 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Stabilizing Native Low-Rank LLM Pretraining.

Paul Janson, Edouard Oyallon, Eugene Belilovsky

CoRR, February, 2026

Heterogeneous Low-Bandwidth Pre-Training of LLMs.

Yazan Obeidi, Amir Sarfi, Joel Lidin, Paul Janson, Eugene Belilovsky

CoRR, January, 2026

2025

PyLO: Towards Accessible Learned Optimizers in PyTorch.

Paul Janson, Benjamin Thérien, Quentin Anthony, Xiaolong Huang, Abhinav Moudgil, Eugene Belilovsky

CoRR, June, 2025

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training.

Vaibhav Singh, Paul Janson, Paria Mehrbod, Adam Ibrahim, Irina Rish, Eugene Belilovsky, Benjamin Thérien

CoRR, March, 2025

2024

FewShotNeRF: Meta-Learning-based Novel View Synthesis for Rapid Scene-Specific Adaptation.

Piraveen Sivakumar, Paul Janson, Jathushan Rajasegaran, Thanuja D. Ambegoda

CoRR, 2024

Towards Motion from Video Diffusion Models.

Paul Janson, Tiberiu Popa, Eugene Belilovsky

Proceedings of the Computer Vision - ECCV 2024 Workshops, 2024

Overcoming Generic Knowledge Loss with Selective Parameter Update.

Wenxuan Zhang, Paul Janson, Rahaf Aljundi, Mohamed Elhoseiny

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Overcoming General Knowledge Loss with Selective Parameter Finetuning.

Wenxuan Zhang, Paul Janson, Rahaf Aljundi, Mohamed Elhoseiny

CoRR, 2023

Continual Zero-Shot Learning through Semantically Guided Generative Random Walks.

Wenxuan Zhang, Paul Janson, Kai Yi, Ivan Skorokhodov, Mohamed Elhoseiny

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning.

Paul Janson, Wenxuan Zhang, Rahaf Aljundi, Mohamed Elhoseiny

CoRR, 2022