Prati
Tijmen Blankevoort
Tijmen Blankevoort
Meta Reality Labs
Potvrđena adresa e-pošte na qti.qualcomm.com
Naslov
Citirano
Citirano
Godina
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
5332019
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
4362020
A white paper on neural network quantization
M Nagel, M Fournarakis, RA Amjad, Y Bondarenko, M Van Baalen, ...
arXiv preprint arXiv:2106.08295, 2021
4102021
Lsq+: Improving low-bit quantization through learnable offsets and better initialization
Y Bhalgat, J Lee, M Nagel, T Blankevoort, N Kwak
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2020
2182020
Conditional channel gated networks for task-aware continual learning
D Abati, J Tomczak, T Blankevoort, S Calderara, R Cucchiara, ...
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2020
2092020
Relaxed quantization for discretized neural networks
C Louizos, M Reisser, T Blankevoort, E Gavves, M Welling
arXiv preprint arXiv:1810.01875, 2018
2072018
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
1212020
Understanding and overcoming the challenges of efficient transformer quantization
Y Bondarenko, M Nagel, T Blankevoort
arXiv preprint arXiv:2109.12948, 2021
1052021
Batch-shaping for learning conditional channel gated networks
BE Bejnordi, T Blankevoort, M Welling
arXiv preprint arXiv:1907.06627, 2019
832019
Differentiable joint pruning and quantization for hardware efficiency
Y Wang, Y Lu, T Blankevoort
European Conference on Computer Vision, 259-277, 2020
762020
Overcoming oscillations in quantization-aware training
M Nagel, M Fournarakis, Y Bondarenko, T Blankevoort
International Conference on Machine Learning, 16318-16330, 2022
632022
Gradient Regularization for Quantization Robustness
M Alizadeh, A Behboodi, M Van Baalen, C Louizos, T Blankevoort, ...
arXiv preprint arXiv:2002.07520, 2020
582020
Distilling optimal neural networks: Rapid search in diverse spaces
B Moons, P Noorzad, A Skliar, G Mariani, D Mehta, C Lott, T Blankevoort
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
492021
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
452022
Vera: Vector-based random matrix adaptation
DJ Kopiczko, T Blankevoort, YM Asano
arXiv preprint arXiv:2310.11454, 2023
422023
Learned threshold pruning
K Azarian, Y Bhalgat, J Lee, T Blankevoort
arXiv preprint arXiv:2003.00075, 2020
402020
Quantizable transformers: Removing outliers by helping attention heads do nothing
Y Bondarenko, M Nagel, T Blankevoort
Advances in Neural Information Processing Systems 36, 2024
332024
Neural network quantization with ai model efficiency toolkit (aimet)
S Siddegowda, M Fournarakis, M Nagel, T Blankevoort, C Patel, ...
arXiv preprint arXiv:2201.08442, 2022
272022
Taxonomy and evaluation of structured compression of convolutional neural networks
A Kuzmin, M Nagel, S Pitre, S Pendyam, T Blankevoort, M Welling
arXiv preprint arXiv:1912.09802, 2019
222019
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
192023
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20