Следене
Francesco Visin
Francesco Visin
Senior Research Scientist at Google DeepMind
Потвърден имейл адрес: google.com
Заглавие
Позовавания
Позовавания
Година
A guide to convolution arithmetic for deep learning
V Dumoulin, F Visin
arXiv preprint arXiv:1603.07285, 2016
27082016
Theano: A Python framework for fast computation of mathematical expressions
R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ...
arXiv e-prints, arXiv: 1605.02688, 2016
1114*2016
Pixelvae: A latent variable model for natural images
I Gulrajani, K Kumar, F Ahmed, AA Taiga, F Visin, D Vazquez, A Courville
arXiv preprint arXiv:1611.05013, 2016
4172016
Reseg: A recurrent neural network-based model for semantic segmentation
F Visin, A Romero, K Cho, M Matteucci, M Ciccone, K Kastner, Y Bengio, ...
2016 IEEE conference on computer vision and pattern recognition workshops …, 2016
416*2016
Renet: A recurrent neural network based alternative to convolutional networks
F Visin, K Kastner, K Cho, M Matteucci, A Courville, Y Bengio
arXiv preprint arXiv:1505.00393, 2015
3542015
Gemma 2: Improving open language models at a practical size
G Team, M Riviere, S Pathak, PG Sessa, C Hardin, S Bhupatiraju, ...
arXiv preprint arXiv:2408.00118, 2024
3202024
Continual unsupervised representation learning
D Rao, F Visin, A Rusu, R Pascanu, YW Teh, R Hadsell
Advances in neural information processing systems 32, 2019
3172019
Meta-learning with warped gradient descent
S Flennerhag, AA Rusu, R Pascanu, F Visin, H Yin, R Hadsell
arXiv preprint arXiv:1909.00025, 2019
2572019
Mollifying networks
C Gulcehre, M Moczulski, F Visin, Y Bengio
arXiv preprint arXiv:1608.04980, 2016
642016
Small data, big decisions: Model selection in the small-data regime
J Bornschein, F Visin, S Osindero
International conference on machine learning, 1035-1044, 2020
522020
Multi-view stereo with single-view semantic mesh refinement
A Romanoni, M Ciccone, F Visin, M Matteucci
Proceedings of the IEEE international conference on computer vision …, 2017
312017
Temporal difference uncertainties as a signal for exploration
S Flennerhag, JX Wang, P Sprechmann, F Visin, A Galashov, ...
arXiv preprint arXiv:2010.02255, 2020
162020
Learning rich touch representations through cross-modal self-supervision
M Zambelli, Y Aytar, F Visin, Y Zhou, R Hadsell
Conference on Robot Learning, 1415-1425, 2021
152021
Dataset loaders: a python library to load and preprocess datasets
F Visin, A Romero
https://github.com/fvisin/dataset_loaders, 2016
42016
ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation
F Lattari, M Ciccone, M Matteucci, J Masci, F Visin
arXiv preprint arXiv:1806.05510, 2018
22018
Deep recurrent neural networks for visual scene understanding
F Visin
Politecnico di Milano, 2017
12017
Jackpot! Alignment as a Maximal Lottery
RR Maura-Rivero, M Lanctot, F Visin, K Larson
arXiv preprint arXiv:2501.19266, 2025
2025
Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models
RR Maura-Rivero, C Nagpal, R Patel, F Visin
arXiv preprint arXiv:2501.06248, 2025
2025
Main loop TF: a main loop for Tensorflow and custom data
F Visin
https://github.com/fvisin/main_loop_tf, 2017
2017
Learning rich touch representations through cross-modal self-supervision Supplementary material
M Zambelli, Y Aytar, F Visin, Y Zhou, R Hadsell
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20