Follow
Arian Hosseini
Arian Hosseini
Mila
Verified email at umontreal.ca - Homepage
Title
Cited by
Cited by
Year
Learning to understand goal specifications by modelling reward
D Bahdanau, F Hill, J Leike, E Hughes, A Hosseini, P Kohli, ...
ICLR 2019, 2018
1532018
Fashion-Gen: The Generative Fashion Dataset and Challenge
N Rostamzadeh, S Hosseini, T Boquet, W Stokowiec, Y Zhang, C Jauvin, ...
arXiv preprint arXiv:1806.08317, 2018
1332018
Understanding by Understanding Not: Modeling Negation in Language Models
A Hosseini, S Reddy, D Bahdanau, RD Hjelm, A Sordoni, A Courville
NAACL 2021, 2021
712021
Commonsense mining as knowledge base completion? A study on the impact of novelty
S Jastrzębski, D Bahdanau, S Hosseini, M Noukhovitch, Y Bengio, ...
arXiv preprint arXiv:1804.09259, 2018
272018
Ordered memory
Y Shen, S Tan, A Hosseini, Z Lin, A Sordoni, AC Courville
Advances in Neural Information Processing Systems 32, 2019
252019
On the Compositional Generalization Gap of In-Context Learning
A Hosseini, A Vani, D Bahdanau, A Sordoni, A Courville
arXiv preprint arXiv:2211.08473, 2022
132022
Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference
A Sordoni, X Yuan, MA Côté, M Pereira, A Trischler, Z Xiao, A Hosseini, ...
arXiv preprint arXiv:2306.12509, 2023
102023
V-STaR: Training Verifiers for Self-Taught Reasoners
A Hosseini, X Yuan, N Malkin, A Courville, A Sordoni, R Agarwal
arXiv preprint arXiv:2402.06457, 2024
32024
Joint Prompt Optimization of Stacked LLMs using Variational Inference
A Sordoni, X Yuan, MA Côté, M Pereira, A Trischler, Z Xiao, A Hosseini, ...
Thirty-seventh Conference on Neural Information Processing Systems, 2023
22023
On the reproducibility of gradient-based Meta-Reinforcement Learning baselines
T Deleu, S Guiroy, S Hosseini
2018
The system can't perform the operation now. Try again later.
Articles 1–10