Follow
Mats L.Richter
Mats L.Richter
PostDoc, Mila; Senior Research Scientist at ServiceNow
Verified email at mila.quebec
Title
Cited by
Cited by
Year
Continual Pre-Training of Large Language Models: How to (re) warm your model?
K Gupta, B Thérien, A Ibrahim, ML Richter, Q Anthony, E Belilovsky, I Rish, ...
S-FoMo Workshop at the 40th International Conference on Machine Learning, 2023
352023
Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
P Pernias, D Rampas, ML Richter, C Pal, M Aubreville
(Top 1.2%, Oral) The Twelfth International Conference on Learning …, 2024
25*2024
(Input) size matters for CNN classifiers
ML Richter, W Byttner, U Krumnack, A Wiedenroth, L Schallner, J Shenk
Artificial Neural Networks and Machine Learning–ICANN 2021: 30th …, 2021
242021
Should you go deeper? optimizing convolutional neural network architectures without training
ML Richter, J Schöning, A Wiedenroth, U Krumnack
2021 20th IEEE International Conference on Machine Learning and Applications …, 2021
192021
Simple and Scalable Strategies to Continually Pre-train Large Language Models
A Ibrahim, B Thérien, K Gupta, ML Richter, Q Anthony, T Lesort, ...
arXiv preprint arXiv:2403.08763, 2024
142024
AI-Based Crop Rotation for Sustainable Agriculture Worldwide
J Schöning, ML Richter
2021 IEEE Global Humanitarian Technology Conference (GHTC), 142-146, 2021
132021
Feature space saturation during training
ML Richter, J Shenk, W Byttner, A Arpteg, M Huss
British Machine Vision Conference 2021, 2021
9*2021
Receptive field analysis for optimizing convolutional neural network architectures without training
ML Richter, J Schöning, A Wiedenroth, U Krumnack
Deep Learning Applications, Volume 4, 235-261, 2022
8*2022
Automatic wound type classification with convolutional neural networks
L Malihi, J Hüsers, ML Richter, M Moelleken, M Przysucha, D Busch, ...
Advances in Informatics, Management and Technology in Healthcare, 281-284, 2022
62022
Feature space saturation during training
ML Richter, J Shenk, W Byttner, A Arpteg, M Huss
arXiv preprint arXiv:2006.08679, 2020
62020
An image based object recognition system for wound detection and classification of diabetic foot and venous leg ulcers
J Hüsers, M Moelleken, ML Richter, M Przysucha, L Malihi, D Busch, ...
Challenges of Trustable AI and Added-Value on Health, 63-67, 2022
42022
Exploring the Properties and Evolution of Neural Network Eigenspaces during Training
ML Richter, L Malihi, AKP Windler, U Krumnack
MVIP 2022, 2022
12022
Delve: Neural Network Feature Variance Analysis
J Shenk, ML Richter, W Byttner
Journal of Open Source Software 69 (7), 3992, 2022
12022
CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling
M Fortier, ML Richter, O Sonnentag, C Pal
arXiv preprint arXiv:2406.04940, 2024
2024
Can Synthetic Images Improve CNN Performance in Wound Image Classification?
HJ Malihi L, Hübner U, Richter ML, Moelleken M, Przysucha M, Busch D ...
Caring is Sharing – Exploiting the Value in Data for Health and Innovation …, 2023
2023
Analyzing the Inference Process in Deep Convolutional Neural Networks using Principal Eigenfeatures, Saturation and Logistic Regression Probes
ML Richter, L Malihi, AKP Windler, U Krumnack
Journal of Applied Research in Electrical Engineering 2 (1), 1-10, 2023
2023
Towards Efficient Convolutional Neural Architecture Design: Exploring the Properties of Neural Architectures Using Spectral Decomposition and Logistic Regression Probes
ML Richter
University of Osnabrück, 2022
2022
Towards efficient convolutional neural architecture design
ML Richter
Dissertation - University of Osnabrück, 2022
2022
Automatic wound type classification with convolutional neural networks
L Malihi, J Hüsers, ML Richter, M Moelleken, M Przysucha, D Busch, ...
Advances in Informatics, Management and Technology in Healthcare, 281-284, 2022
2022
Go with the Flow: the distribution of information processing in multi-path networks
ML Richter, K Shah, A Wiedenroth, S Bachu, U Krumnack
International Conference on Learning Representations (ICLR) 2022 (Workshop), 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–20