Prati
Ekin Akyürek
Ekin Akyürek
PhD Candidate @ MIT
Potvrđena adresa e-pošte na mit.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
What learning algorithm is in-context learning? investigations with linear models
E Akyürek, D Schuurmans, J Andreas, T Ma, D Zhou
International Conference on Learning Representations, 2023
514*2023
Pre-trained language models for interactive decision-making
S Li, X Puig, C Paxton, Y Du, C Wang, L Fan, T Chen, DA Huang, ...
Advances in Neural Information Processing Systems, 2022
261*2022
Reasoning or reciting? exploring the capabilities and limitations of language models through counterfactual tasks
Z Wu, L Qiu, A Ross, E Akyürek, B Chen, B Wang, N Kim, J Andreas, ...
Annual Conference of the Nations of the Americas Chapter of the Association …, 2024
1802024
Compositional semantic parsing with large language models
A Drozdov, N Schärli, E Akyürek, N Scales, X Song, X Chen, O Bousquet, ...
The Eleventh International Conference on Learning Representations, 2023
1442023
Learning to recombine and resample data for compositional generalization
E Akyürek, AF Akyürek, J Andreas
International Conference on Learning Representations, 2021
1022021
RL4F: Generating natural language feedback with reinforcement learning for repairing model outputs
AF Akyürek, E Akyürek, A Madaan, A Kalyan, P Clark, D Wijaya, ...
Annual Meeting of the Association for Computational Linguistics, 2023
862023
Subspace Regularizers for Few-Shot Class Incremental Learning
AF Akyürek, E Akyürek, D Wijaya, J Andreas
International Conference on Learning Representations, 2022
812022
Towards tracing factual knowledge in language models back to the training data
E Akyürek, T Bolukbasi, F Liu, B Xiong, I Tenney, J Andreas, K Guu
Conference on Empirical Methods in Natural Language Processing (Findings), 2022
772022
In-context language learning: Arhitectures and algorithms
E Akyürek, B Wang, Y Kim, J Andreas
International Conference on Machine Learning, 2024
65*2024
Lexicon Learning for Few-Shot Neural Sequence Modeling
E Akyürek, J Andreas
Annual Meeting of the Association for Computational Linguistics, 2021
49*2021
Morphological analysis using a sequence decoder
E Akyürek, E Dayanık, D Yuret
Transactions of the Association for Computational Linguistics 7, 2019
31*2019
Compositionality as lexical symmetry
E Akyürek, J Andreas
Annual Meeting of the Association for Computational Linguistics, 2023
22*2023
Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models
AA Ivanova, A Sathe, B Lipkin, U Kumar, S Radkani, TH Clark, C Kauf, ...
arXiv preprint arXiv:2405.09605, 2024
13*2024
The surprising effectiveness of test-time training for abstract reasoning
E Akyürek, M Damani, L Qiu, H Guo, Y Kim, J Andreas
arXiv preprint arXiv:2411.07279, 2024
92024
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
A Feyza Akyürek, E Akyürek, L Choshen, D Wijaya, J Andreas
Annual Meeting of the Association for Computational Linguistics (Findings), 2024
9*2024
Through the glance mug: A familiar artefact to support opportunistic search in meetings
A Börütecene, I Bostan, E Akyürek, A Sabuncuoglu, I Temuzkusu, Ç Genç, ...
Proceedings of the Twelfth International Conference on Tangible, Embedded …, 2018
92018
Learning Linear Attention in Polynomial Time
M Yau, E Akyürek, J Mao, JB Tenenbaum, S Jegelka, J Andreas
arXiv preprint arXiv:2410.10101, 2024
12024
Backpropagation through Back Substitution with a Backslash
A Edelman, E Akyürek, Y Wang
SIAM Journal on Matrix Analysis and Applications 45 (1), 2024
2024
Notes on Teaching GPT-3 Adding Numbers
E Akyürek, AF Akyürek
https://lingo.csail.mit.edu/blog/arithmetic_gpt3, 2022
2022
Compositional Models for Few Shot Sequence Learning
E Akyurek
Massachusetts Institute of Technology, 2021
2021
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20