Follow
Daniel Y Fu
Daniel Y Fu
Graduate Student, Stanford University
Verified email at cs.stanford.edu - Homepage
Title
Cited by
Cited by
Year
Flashattention: Fast and memory-efficient exact attention with io-awareness
T Dao, D Fu, S Ermon, A Rudra, C Ré
Advances in Neural Information Processing Systems 35, 16344-16359, 2022
5452022
Fast and three-rious: Speeding up weak supervision with triplet methods
D Fu, M Chen, F Sala, S Hooper, K Fatahalian, C Ré
International Conference on Machine Learning, 3280-3291, 2020
1112020
Hungry hungry hippos: Towards language modeling with state space models
DY Fu, T Dao, KK Saab, AW Thomas, A Rudra, C Ré
The Eleventh International Conference on Learning Representations, 2023
1012023
Hyena hierarchy: Towards larger convolutional language models
M Poli, S Massaroli, E Nguyen, DY Fu, T Dao, S Baccus, Y Bengio, ...
arXiv preprint arXiv:2302.10866, 2023
932023
Rekall: Specifying video events using compositions of spatiotemporal labels
DY Fu, W Crichton, J Hong, X Yao, H Zhang, A Truong, A Narayan, ...
arXiv preprint arXiv:1910.02993, 2019
532019
High-throughput generative inference of large language models with a single gpu
Y Sheng, L Zheng, B Yuan, Z Li, M Ryabinin, DY Fu, Z Xie, B Chen, ...
arXiv preprint arXiv:2303.06865, 2023
392023
Multi-resolution weak supervision for sequential data
P Varma, F Sala, S Sagawa, J Fries, D Fu, S Khattar, A Ramamoorthy, ...
Advances in Neural Information Processing Systems 32, 2019
352019
Perfectly balanced: Improving transfer and robustness of supervised contrastive learning
M Chen, DY Fu, A Narayan, M Zhang, Z Song, K Fatahalian, C Ré
International Conference on Machine Learning, 3090-3122, 2022
332022
Simple hardware-efficient long convolutions for sequence modeling
DY Fu, EL Epstein, E Nguyen, AW Thomas, M Zhang, T Dao, A Rudra, ...
arXiv preprint arXiv:2302.06646, 2023
242023
Shoring up the foundations: Fusing model embeddings and weak supervision
MF Chen, DY Fu, D Adila, M Zhang, F Sala, K Fatahalian, C Ré
Uncertainty in Artificial Intelligence, 357-367, 2022
24*2022
Analysis of faces in a decade of us cable tv news
J Hong, W Crichton, H Zhang, DY Fu, J Ritchie, J Barenholtz, B Hannel, ...
KDD'21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery …, 2021
20*2021
Tabi: Type-aware bi-encoders for open-domain entity retrieval
M Leszczynski, DY Fu, MF Chen, C Ré
arXiv preprint arXiv:2204.08173, 2022
102022
Orexinergic neurotransmission in temperature responses to methamphetamine and stress: mathematical modeling as a data assimilation approach
A Behrouzvaziri, D Fu, P Tan, Y Yoo, MV Zaretskaia, DE Rusyniak, ...
PLoS One 10 (5), e0126719, 2015
82015
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness, June 2022
T Dao, DY Fu, S Ermon, A Rudra, C Ré
URL http://arxiv. org/abs/2205.14135, 0
8
Monarch mixer: A simple sub-quadratic gemm-based architecture
D Fu, S Arora, J Grogan, I Johnson, ES Eyuboglu, A Thomas, B Spector, ...
Advances in Neural Information Processing Systems 36, 2024
62024
Automatic parallelization of sequential programs
P Kraft, A Waterland, DY Fu, A Gollamudi, S Szulanski, M Seltzer
arXiv preprint arXiv:1809.07684, 2018
52018
Chaos and robustness in a single family of genetic oscillatory networks
D Fu, P Tan, A Kuznetsov, YI Molkov
PloS one 9 (3), e90666, 2014
52014
The details matter: Preventing class collapse in supervised contrastive learning
DY Fu, MF Chen, M Zhang, K Fatahalian, C Ré
Computer Sciences & Mathematics Forum 3 (1), 4, 2022
42022
Influencing flock formation in low-density settings
DY Fu, ES Wang, PM Krafft, BJ Grosz
arXiv preprint arXiv:1804.08667, 2018
42018
Laughing hyena distillery: Extracting compact recurrences from convolutions
S Massaroli, M Poli, D Fu, H Kumbong, R Parnichkun, D Romero, ...
Advances in Neural Information Processing Systems 36, 2024
22024
The system can't perform the operation now. Try again later.
Articles 1–20