Azalia Mirhoseini
Azalia Mirhoseini
Assistant Professor of Computer Science, Stanford
Verified email at - Homepage
Cited by
Cited by
Outrageously large neural networks: The sparsely-gated mixture-of-experts layer
N Shazeer, A Mirhoseini, K Maziarz, A Davis, Q Le, G Hinton, J Dean
arXiv preprint arXiv:1701.06538, 2017
Constitutional ai: Harmlessness from ai feedback
Y Bai, S Kadavath, S Kundu, A Askell, J Kernion, A Jones, A Chen, ...
arXiv preprint arXiv:2212.08073, 2022
A graph placement methodology for fast chip design
A Mirhoseini, A Goldie, M Yazgan, JW Jiang, E Songhori, S Wang, YJ Lee, ...
Nature 594 (7862), 207-212, 2021
Device placement optimization with reinforcement learning
A Mirhoseini, H Pham, QV Le, B Steiner, R Larsen, Y Zhou, N Kumar, ...
International conference on machine learning, 2430-2439, 2017
Chip placement with deep reinforcement learning
A Mirhoseini, A Goldie, M Yazgan, J Jiang, E Songhori, S Wang, YJ Lee, ...
arXiv preprint arXiv:2004.10746, 2020
Representing long-range context for graph neural networks with global attention
Z Wu, P Jain, M Wright, A Mirhoseini, JE Gonzalez, I Stoica
Advances in Neural Information Processing Systems 34, 13266-13279, 2021
{FLAME}: Taming backdoors in federated learning
TD Nguyen, P Rieger, R De Viti, H Chen, BB Brandenburg, H Yalame, ...
31st USENIX Security Symposium (USENIX Security 22), 1415-1432, 2022
A hierarchical model for device placement
A Mirhoseini, A Goldie, H Pham, B Steiner, QV Le, J Dean
International Conference on Learning Representations, 2018
SAFELearn: Secure aggregation for private federated learning
H Fereidooni, S Marchal, M Miettinen, A Mirhoseini, H Möllering, ...
2021 IEEE Security and Privacy Workshops (SPW), 56-62, 2021
A unified framework for multimodal submodular integrated circuits trojan detection
F Koushanfar, A Mirhoseini
IEEE Transactions on Information Forensics and Security 6 (1), 162-174, 2010
Optimizing task recommendations in context-aware mobile crowdsourcing
S Nath, M Goraczko, J Liu, A Mirhoseini
US Patent 9,911,088, 2018
The capacity for moral self-correction in large language models
D Ganguli, A Askell, N Schiefer, TI Liao, K Lukošiūtė, A Chen, A Goldie, ...
arXiv preprint arXiv:2302.07459, 2023
Deep mixture of experts via shallow embedding
X Wang, F Yu, L Dunlap, YA Ma, R Wang, A Mirhoseini, T Darrell, ...
Uncertainty in artificial intelligence, 552-562, 2020
Idetic: A high-level synthesis approach for enabling long computations on transiently-powered ASICs
A Mirhoseini, EM Songhori, F Koushanfar
2013 IEEE International Conference on Pervasive Computing and Communications …, 2013
Flguard: Secure and private federated learning
TD Nguyen, P Rieger, MH Yalame, H Möllering, H Fereidooni, S Marchal, ...
Crytography and Security, 2021
Gap: Generalizable approximate graph partitioning framework
A Nazi, W Hang, A Goldie, S Ravi, A Mirhoseini
arXiv preprint arXiv:1903.00614, 2019
Delight: Adding energy dimension to deep neural networks
BD Rouhani, A Mirhoseini, F Koushanfar
Proceedings of the 2016 International Symposium on Low Power Electronics and …, 2016
Measuring progress on scalable oversight for large language models
SR Bowman, J Hyun, E Perez, E Chen, C Pettit, S Heiner, K Lukošiūtė, ...
arXiv preprint arXiv:2211.03540, 2022
Placement optimization with deep reinforcement learning
A Goldie, A Mirhoseini
Proceedings of the 2020 International Symposium on Physical Design, 3-7, 2020
Transferable graph optimizers for ml compilers
Y Zhou, S Roy, A Abdolrashidi, D Wong, P Ma, Q Xu, H Liu, ...
Advances in Neural Information Processing Systems 33, 13844-13855, 2020
The system can't perform the operation now. Try again later.
Articles 1–20