Sledovat
Joshua Ainslie
Joshua Ainslie
E-mailová adresa ověřena na: google.com
Název
Citace
Citace
Rok
Big bird: Transformers for longer sequences
M Zaheer, G Guruganesh, KA Dubey, J Ainslie, C Alberti, S Ontanon, ...
Advances in neural information processing systems 33, 17283-17297, 2020
18632020
Gemini: a family of highly capable multimodal models
G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ...
arXiv preprint arXiv:2312.11805, 2023
5682023
Fnet: Mixing tokens with fourier transforms
J Lee-Thorp, J Ainslie, I Eckstein, S Ontanon
arXiv preprint arXiv:2105.03824, 2021
4022021
ETC: Encoding long and structured inputs in transformers
J Ainslie, S Ontanon, C Alberti, V Cvicek, Z Fisher, P Pham, A Ravula, ...
arXiv preprint arXiv:2004.08483, 2020
3392020
LongT5: Efficient text-to-text transformer for long sequences
M Guo, J Ainslie, D Uthus, S Ontanon, J Ni, YH Sung, Y Yang
arXiv preprint arXiv:2112.07916, 2021
2122021
Gqa: Training generalized multi-query transformer models from multi-head checkpoints
J Ainslie, J Lee-Thorp, M de Jong, Y Zemlyanskiy, F Lebrón, S Sanghai
arXiv preprint arXiv:2305.13245, 2023
1232023
Realformer: Transformer likes residual attention
R He, A Ravula, B Kanagal, J Ainslie
arXiv preprint arXiv:2012.11747, 2020
902020
Formnet: Structural encoding beyond sequential modeling in form document information extraction
CY Lee, CL Li, T Dozat, V Perot, G Su, N Hua, J Ainslie, R Wang, Y Fujii, ...
arXiv preprint arXiv:2203.08411, 2022
682022
Making transformers solve compositional tasks
S Ontanon, J Ainslie, V Cvicek, Z Fisher
arXiv preprint arXiv:2108.04378, 2021
612021
Colt5: Faster long-range transformers with conditional computation
J Ainslie, T Lei, M de Jong, S Ontañón, S Brahma, Y Zemlyanskiy, ...
arXiv preprint arXiv:2303.09752, 2023
412023
Encoding long and structured data in transformers
J Ainslie, S Ontanon, C Alberti, P Pham, A Ravula, S Sanghai
arXiv preprint arXiv:2004.08483 2, 2020
342020
Sparse upcycling: Training mixture-of-experts from dense checkpoints
A Komatsuzaki, J Puigcerver, J Lee-Thorp, CR Ruiz, B Mustafa, J Ainslie, ...
arXiv preprint arXiv:2212.05055, 2022
302022
FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference
M de Jong, Y Zemlyanskiy, J Ainslie, N FitzGerald, S Sanghai, F Sha, ...
arXiv preprint arXiv:2212.08153, 2022
202022
Fnet: Mixing tokens with fourier transforms. arXiv 2021
J Lee-Thorp, J Ainslie, I Eckstein, S Ontanon
arXiv preprint arXiv:2105.03824, 2021
192021
Improving compositional generalization in classification tasks via structure annotations
J Kim, P Ravikumar, J Ainslie, S Ontañón
arXiv preprint arXiv:2106.10434, 2021
152021
Readtwice: Reading very large documents with memories
Y Zemlyanskiy, J Ainslie, M de Jong, P Pham, I Eckstein, F Sha
arXiv preprint arXiv:2105.04241, 2021
132021
ETC: Encoding long and structured inputs in transformers
A Ravula, C Alberti, J Ainslie, L Yang, PM Pham, Q Wang, S Ontanon, ...
Proceedings of the 2020 Conference on Empirical Methods in Natural Language …, 2020
122020
Conditional adapters: Parameter-efficient transfer learning with fast inference
T Lei, J Bai, S Brahma, J Ainslie, K Lee, Y Zhou, N Du, V Zhao, Y Wu, B Li, ...
Advances in Neural Information Processing Systems 36, 2024
112024
Generate-and-retrieve: Use your predictions to improve retrieval for semantic parsing
Y Zemlyanskiy, M de Jong, J Ainslie, P Pasupat, P Shaw, L Qiu, ...
arXiv preprint arXiv:2209.14899, 2022
112022
Functional interpolation for relative positions improves long context transformers
S Li, C You, G Guruganesh, J Ainslie, S Ontanon, M Zaheer, S Sanghai, ...
arXiv preprint arXiv:2310.04418, 2023
102023
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–20