Sainbayar Sukhbaatar
Sainbayar Sukhbaatar
Research Scientist, Facebook AI Research
Verified email at - Homepage
Cited by
Cited by
End-To-End Memory Networks
S Sukhbaatar, A Szlam, J Weston, R Fergus
Learning multiagent communication with backpropagation
S Sukhbaatar, A Szlam, R Fergus
Advances in Neural Information Processing Systems, 2244-2252, 2016
Training Convolutional Networks with Noisy Labels
S Sukhbaatar, J Bruna, M Paluri, L Bourdev, R Fergus
Accepted as a workshop contribution at ICLR 2015, 2014
Simple baseline for visual question answering
B Zhou, Y Tian, S Sukhbaatar, A Szlam, R Fergus
arXiv preprint arXiv:1512.02167, 2015
Intrinsic motivation and automatic curricula via asymmetric self-play
S Sukhbaatar, Z Lin, I Kostrikov, G Synnaeve, A Szlam, R Fergus
arXiv preprint arXiv:1703.05407, 2017
Adaptive attention span in transformers
S Sukhbaatar, E Grave, P Bojanowski, A Joulin
arXiv preprint arXiv:1905.07799, 2019
Learning when to communicate at scale in multiagent cooperative and competitive tasks
A Singh, T Jain, S Sukhbaatar
arXiv preprint arXiv:1812.09755, 2018
Mazebase: A sandbox for learning from games
S Sukhbaatar, A Szlam, G Synnaeve, S Chintala, R Fergus
arXiv preprint arXiv:1511.07401, 2015
Composable planning with attributes
A Zhang, S Sukhbaatar, A Lerer, A Szlam, R Fergus
International Conference on Machine Learning, 5842-5851, 2018
Augmenting self-attention with persistent memory
S Sukhbaatar, E Grave, G Lample, H Jegou, A Joulin
arXiv preprint arXiv:1907.01470, 2019
Robust Generation of Dynamical Patterns in Human Motion by a Deep Belief Nets
S Sukhbaatar, T Makino, K Aihara, T Chikayama
Asian Conference on Machine Learning, 231--246, 2011
End-to-end memory networks
JE Weston, AD Szlam, RD Fergus, S Sukhbaatar
US Patent 10,664,744, 2020
Learning goal embeddings via self-play for hierarchical reinforcement learning
S Sukhbaatar, E Denton, A Szlam, R Fergus
arXiv preprint arXiv:1811.09083, 2018
Addressing Some Limitations of Transformers with Feedback Memory
A Fan, T Lavril, E Grave, A Joulin, S Sukhbaatar
arXiv preprint arXiv:2002.09402, 2020
Learning to visually navigate in photorealistic environments without any supervision
L Mezghani, S Sukhbaatar, A Szlam, A Joulin, P Bojanowski
arXiv preprint arXiv:2004.04954, 2020
Auto-pooling: Learning to improve invariance of image features from image sequences
S Sukhbaatar, T Makino, K Aihara
arXiv preprint arXiv:1301.3323, 2013
Training hybrid language models by marginalizing over segmentations
E Grave, S Sukhbaatar, P Bojanowski, A Joulin
Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019
Hash Layers For Large Sparse Models
S Roller, S Sukhbaatar, A Szlam, J Weston
arXiv preprint arXiv:2106.04426, 2021
Not All Memories are Created Equal: Learning to Forget by Expiring
S Sukhbaatar, D Ju, S Poff, S Roller, A Szlam, J Weston, A Fan
arXiv preprint arXiv:2105.06548, 2021
Memory-Augmented Reinforcement Learning for Image-Goal Navigation
L Mezghani, S Sukhbaatar, T Lavril, O Maksymets, D Batra, P Bojanowski, ...
arXiv preprint arXiv:2101.05181, 2021
The system can't perform the operation now. Try again later.
Articles 1–20