Please note that ISTA Research Explorer no longer supports Internet Explorer versions 8 or 9 (or earlier).
We recommend upgrading to the latest Internet Explorer, Google Chrome, or Firefox.
5 Publications
2020 | Published | Conference Paper | IST-REx-ID: 14326 | 
Locatello, Francesco, Object-centric learning with slot attention. 34th International Conference on Neural Information Processing Systems 33. 2020
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2020 | Published | Conference Paper | IST-REx-ID: 15086 |
Faghri, F., Tabrizian, I., Markov, I., Alistarh, D.-A., Roy, D., & Ramezani-Kebrya, A. (2020). Adaptive gradient quantization for data-parallel SGD. In Advances in Neural Information Processing Systems (Vol. 33). Vancouver, Canada: Neural Information Processing Systems Foundation.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2020 | Published | Conference Paper | IST-REx-ID: 9632 |
Singh, S. P., & Alistarh, D.-A. (2020). WoodFisher: Efficient second-order approximation for neural network compression (Vol. 33, pp. 18098–18109). Presented at the NeurIPS: Conference on Neural Information Processing Systems, Vancouver, Canada: Neural Information Processing Systems Foundation.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2020 | Published | Conference Paper | IST-REx-ID: 9631 |
Aksenov, V., Alistarh, D.-A., & Korhonen, J. (2020). Scalable belief propagation via relaxed scheduling (Vol. 33, pp. 22361–22372). Presented at the NeurIPS: Conference on Neural Information Processing Systems, Vancouver, Canada: Neural Information Processing Systems Foundation.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2020 | Published | Conference Paper | IST-REx-ID: 8188 |
Henderson, P. M., & Lampert, C. (2020). Unsupervised object-centric video generation and decomposition in 3D. In 34th Conference on Neural Information Processing Systems (Vol. 33, pp. 3106–3117). Vancouver, Canada: Neural Information Processing Systems Foundation.
[Preprint]
View
| Download Preprint (ext.)
| arXiv