Volgen
Mart van Baalen
Mart van Baalen
Andere namenMarinus van Baalen, Marinus Willem van Baalen
Research Scientist (Senior Staff), Qualcomm AI Research
Geverifieerd e-mailadres voor qti.qualcomm.com
Titel
Geciteerd door
Geciteerd door
Jaar
Data-free quantization through weight equalization and bias correction
M Nagel, M Baalen, T Blankevoort, M Welling
Proceedings of the IEEE/CVF international conference on computer vision …, 2019
6352019
A white paper on neural network quantization
M Nagel, M Fournarakis, RA Amjad, Y Bondarenko, M Van Baalen, ...
arXiv preprint arXiv:2106.08295, 2021
6222021
Up or down? adaptive rounding for post-training quantization
M Nagel, RA Amjad, M Van Baalen, C Louizos, T Blankevoort
International conference on machine learning, 7197-7206, 2020
5842020
Bayesian bits: Unifying quantization and pruning
M Van Baalen, C Louizos, M Nagel, RA Amjad, Y Wang, T Blankevoort, ...
Advances in neural information processing systems 33, 5741-5752, 2020
1442020
Fp8 quantization: The power of the exponent
A Kuzmin, M Van Baalen, Y Ren, M Nagel, J Peters, T Blankevoort
Advances in Neural Information Processing Systems 35, 14651-14662, 2022
732022
Gradient Regularization for Quantization Robustness
M Alizadeh, A Behboodi, M Van Baalen, C Louizos, T Blankevoort, ...
arXiv preprint arXiv:2002.07520, 2020
642020
Pruning vs quantization: Which is better?
A Kuzmin, M Nagel, M Van Baalen, A Behboodi, T Blankevoort
Advances in neural information processing systems 36, 62414-62427, 2023
502023
A white paper on neural network quantization. arXiv 2021
M Nagel, M Fournarakis, RA Amjad, Y Bondarenko, M van Baalen, ...
arXiv preprint arXiv:2106.08295 4, 0
39
FP8 versus INT8 for efficient deep learning inference
M Van Baalen, A Kuzmin, SS Nair, Y Ren, E Mahurin, C Patel, ...
arXiv preprint arXiv:2303.17951, 2023
382023
The llm surgeon
TFA van der Ouderaa, M Nagel, M Van Baalen, YM Asano, T Blankevoort
arXiv preprint arXiv:2312.17244, 2023
302023
Deep matrix factorization for recommendation
M van Baalen
Master's Thesis, Univ. of Amsterdam, Sep 30, 2016
222016
Gptvq: The blessing of dimensionality for llm quantization
M Van Baalen, A Kuzmin, M Nagel, P Couperus, C Bastoul, E Mahurin, ...
arXiv preprint arXiv:2402.15319, 2024
192024
Cyclical pruning for sparse neural networks
S Srinivas, A Kuzmin, M Nagel, M van Baalen, A Skliar, T Blankevoort
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2022
192022
A practical mixed precision algorithm for post-training quantization
NP Pandey, M Nagel, M van Baalen, Y Huang, C Patel, T Blankevoort
arXiv preprint arXiv:2302.05397, 2023
122023
Simulated quantization, real power savings
M van Baalen, B Kahne, E Mahurin, A Kuzmin, A Skliar, M Nagel, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
102022
FP8 versus INT8 for efficient deep learning inference
M Baalen, A Kuzmin, SS Nair, Y Ren, E Mahurin, C Patel, S Subramanian, ...
arXiv preprint arXiv:2303.17951, 2023
62023
Qbitopt: Fast and accurate bitwidth reallocation during training
J Peters, M Fournarakis, M Nagel, M Van Baalen, T Blankevoort
Proceedings of the IEEE/CVF international conference on computer vision …, 2023
62023
Quantized sparse weight decomposition for neural network compression
A Kuzmin, M van Baalen, M Nagel, A Behboodi
arXiv preprint arXiv:2207.11048, 2022
32022
Mixture of cache-conditional experts for efficient mobile device inference
A Skliar, T van Rozendaal, R Lepert, T Boinovski, M van Baalen, M Nagel, ...
arXiv preprint arXiv:2412.00099, 2024
22024
Rapid switching and multi-adapter fusion via sparse high rank adapters
K Bhardwaj, NP Pandey, S Priyadarshi, V Ganapathy, R Esteves, ...
arXiv preprint arXiv:2407.16712, 2024
22024
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20