Jovita Lukasik
Jovita Lukasik
Verified email at
Cited by
Cited by
Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks
A Zela, J Siems, L Zimmer, J Lukasik, M Keuper, F Hutter
International Conference on Learning Representations (ICLR), 2020
Smooth variational graph embeddings for efficient neural architecture search
J Lukasik, D Friede, A Zela, F Hutter, M Keuper
2021 International Joint Conference on Neural Networks (IJCNN), 1-8, 2021
Neural architecture performance prediction using graph neural networks
J Lukasik, D Friede, H Stuckenschmidt, M Keuper
Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen …, 2021
Learning where to look–generative nas is surprisingly efficient
J Lukasik*, S Jung*, M Keuper
European Conference on Computer Vision, 257-273, 2022
Neural architecture design and robustness: A dataset
S Jung*, J Lukasik*, M Keuper
International Conference on Learning Representations (ICLR), 2023
A variational-sequential graph autoencoder for neural architecture performance prediction
D Friede, J Lukasik, H Stuckenschmidt, M Keuper
arXiv preprint arXiv:1912.05317, 2019
Improving Native CNN Robustness with Filter Frequency Regularization
J Lukasik*, P Gavrikov*, J Keuper, M Keuper
Transactions on Machine Learning Research, 2023
A benders decomposition approach to correlation clustering
J Lukasik, M Keuper, M Singh, J Yarkony
2020 IEEE/ACM Workshop on Machine Learning in High Performance Computing …, 2020
DARTS for inverse problems: A study on stability
J Geiping, J Lukasik, M Keuper, M Moeller
NeurIPS 2021 Workshop on Deep Learning and Inverse Problems, 2021
Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
P Gavrikov, J Lukasik, S Jung, R Geirhos, B Lamm, MJ Mirza, M Keuper, ...
arXiv preprint arXiv:2403.09193, 2024
An Evaluation of Zero-Cost Proxies-From Neural Architecture Performance Prediction to Model Robustness
J Lukasik, M Moeller, M Keuper
DAGM German Conference on Pattern Recognition, 624-638, 2023
Differentiable Architecture Search: a One-Shot Method?
J Lukasik, J Geiping, M Moeller, M Keuper
AutoML Conference 2023, 2023
An Evaluation of Zero-Cost Proxies--from Neural Architecture Performance to Model Robustness
J Lukasik, M Moeller, M Keuper
arXiv preprint arXiv:2307.09365, 2023
Topology Learning for Prediction, Generation, and Robustness in Neural Architecture Search
J Lukasik
Implicit Representations for Image Segmentation
JP Schneider, F Mishal, J Lukasik, A Kolb, M Keuper, M Moeller
First Workshop on Unifying Representations in Neural Models, 1-6, 2022
Is Differentiable Architecture Search truly a One-Shot Method?
J Geiping, J Lukasik, M Keuper, M Moeller
arXiv preprint arXiv:2108.05647, 2021
DARTS for Inverse Problems: a Study on Hyperparameter Sensitivity.
J Geiping, J Lukasik, M Keuper, M Moeller
arXiv preprint arXiv:2108.05647, 2021
The system can't perform the operation now. Try again later.
Articles 1–17