Obserwuj
Maya Okawa
Maya Okawa
NTT Research, Inc / Harvard University
Zweryfikowany adres z fas.harvard.edu
Tytuł
Cytowane przez
Cytowane przez
Rok
Deep mixture point processes: Spatio-temporal event prediction with rich contextual information
M Okawa, T Iwata, T Kurashima, Y Tanaka, H Toda, N Ueda
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019
672019
Spatially aggregated Gaussian processes with multivariate areal outputs
Y Tanaka, T Tanaka, T Iwata, T Kurashima, M Okawa, Y Akagi, H Toda
Advances in Neural Information Processing Systems 32, 2019
302019
Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
M Okawa, ES Lubana, R Dick, H Tanaka
Advances in Neural Information Processing Systems (NeurIPS) 36, 2023
282023
Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
M Okawa, T Iwata
Proceedings of the 28th ACM SIGKDD International Conference on Knowledge …, 2022
212022
Predicting traffic accidents with event recorder data
Y Takimoto, Y Tanaka, T Kurashima, S Yamamoto, M Okawa, H Toda
Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Prediction …, 2019
192019
Refining coarse-grained spatial data using auxiliary spatial data sets with various granularities
Y Tanaka, T Iwata, T Tanaka, T Kurashima, M Okawa, H Toda
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 5091-5099, 2019
172019
Online traffic flow prediction using convolved bilinear poisson regression
M Okawa, H Kim, H Toda
2017 18th IEEE International Conference on Mobile Data Management (MDM), 134-143, 2017
172017
Real-time and proactive navigation via spatio-temporal prediction
N Ueda, F Naya, H Shimizu, T Iwata, M Okawa, H Sawada
Adjunct Proceedings of the 2015 ACM International Joint Conference on …, 2015
172015
Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes
M Okawa, T Iwata, Y Tanaka, H Toda, T Kurashima, H Kashima
Proceedings of the 27th ACM SIGKDD International Conference on Knowledge …, 2021
122021
Context-aware spatio-temporal event prediction via convolutional Hawkes processes
M Okawa, T Iwata, Y Tanaka, H Toda, T Kurashima, H Kashima
Machine Learning Journal (ECML-PKDD Journal Track), 2022
72022
Emergence of hidden capabilities: Exploring learning dynamics in concept space
CF Park, M Okawa, A Lee, ES Lubana, H Tanaka
arXiv preprint arXiv:2406.19370, 2024
32024
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
M Khona, M Okawa, J Hula, R Ramesh, K Nishi, R Dick, ES Lubana, ...
arXiv preprint arXiv:2402.07757, 2024
22024
Deep Mixture Point Processes
M Okawa, T Iwata, T Kurashima, Y Tanaka, H Toda, N Ueda, H Kashima
Transactions of the Japanese Society for Artificial Intelligence 36 (5), C-L37, 2021
22021
Marked temporal point processes for trip demand prediction in bike sharing systems
M Okawa, Y Tanaka, T Kurashima, H Toda, T Yamada
IEICE TRANSACTIONS on Information and Systems 102 (9), 1635-1643, 2019
22019
Deep Mixture Point Processes
M Okawa, T Iwata, T Kurashima, Y Tanaka, H Toda, N Ueda
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019
22019
Event occurrence time learning device, event occurrence time estimation device, event occurrence time learning method, event occurrence time estimation method, event occurrence …
Y Takimoto, Y Tanaka, T Kurashima, S Yamamoto, M Okawa, H Toda
US Patent App. 17/613,062, 2022
12022
Spatio-temporal event data estimating device, method, and program
M Okawa, H Toda
US Patent App. 17/058,613, 2021
12021
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
K Nishi, M Okawa, R Ramesh, M Khona, ES Lubana, H Tanaka
arXiv preprint arXiv:2410.17194, 2024
2024
Dynamics of Concept Learning and Compositional Generalization
Y Yang, CF Park, ES Lubana, M Okawa, W Hu, H Tanaka
arXiv preprint arXiv:2410.08309, 2024
2024
Prediction apparatus, prediction method and program
M Okawa, H Toda
US Patent App. 18/558,460, 2024
2024
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20