Beyond the imitation game: Quantifying and extrapolating the capabilities of language models A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ... arXiv preprint arXiv:2206.04615, 2022 | 1186 | 2022 |
Convit: Improving vision transformers with soft convolutional inductive biases S d’Ascoli, H Touvron, ML Leavitt, AS Morcos, G Biroli, L Sagun International conference on machine learning, 2286-2296, 2021 | 905 | 2021 |
Sustained activity encoding working memories: not fully distributed ML Leavitt, D Mendoza-Halliday, JC Martinez-Trujillo Trends in Neurosciences 40 (6), 328-346, 2017 | 200 | 2017 |
Correlated variability modifies working memory fidelity in primate prefrontal neuronal ensembles ML Leavitt, F Pieper, AJ Sachs, JC Martinez-Trujillo Proceedings of the National Academy of Sciences 114 (12), E2494-E2503, 2017 | 115 | 2017 |
Vissl P Goyal, Q Duval, J Reizenstein, M Leavitt, M Xu, B Lefaudeux, M Singh, ... | 93 | 2021 |
Towards falsifiable interpretability research ML Leavitt, A Morcos arXiv preprint arXiv:2010.12016, 2020 | 91 | 2020 |
Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs ML Leavitt, A Morcos arXiv preprint arXiv:2003.01262, 2020 | 57 | 2020 |
A quadrantic bias in prefrontal representation of visual-mnemonic space ML Leavitt, F Pieper, AJ Sachs, JC Martinez-Trujillo Cerebral Cortex 28 (7), 2405-2421, 2018 | 42 | 2018 |
Sudden drops in the loss: Syntax acquisition, phase transitions, and simplicity bias in MLMs A Chen, R Shwartz-Ziv, K Cho, ML Leavitt, N Saphra arXiv preprint arXiv:2309.07311, 2023 | 37 | 2023 |
Structure of spike count correlations reveals functional interactions between neurons in dorsolateral prefrontal cortex area 8a of behaving primates ML Leavitt, F Pieper, A Sachs, R Joober, JC Martinez-Trujillo PloS one 8 (4), e61503, 2013 | 33 | 2013 |
Single-trial decoding of intended eye movement goals from lateral prefrontal cortex neural ensembles CB Boulay, F Pieper, M Leavitt, J Martinez-Trujillo, AJ Sachs Journal of neurophysiology 115 (1), 486-499, 2016 | 22 | 2016 |
Linking average-and worst-case perturbation robustness via class selectivity and dimensionality ML Leavitt, A Morcos arXiv preprint arXiv:2010.07693, 2020 | 12* | 2020 |
A normalization circuit underlying coding of spatial attention in primate lateral prefrontal cortex L Duong, M Leavitt, F Pieper, A Sachs, J Martinez-Trujillo eneuro 6 (2), 2019 | 12 | 2019 |
Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models Z Ankner, C Blakeney, K Sreenivasan, M Marion, ML Leavitt, M Paul arXiv preprint arXiv:2405.20541, 2024 | 9 | 2024 |
Knowledge distillation for efficient sequences of training runs X Liu, A Leonardi, L Yu, C Gilmer-Hill, M Leavitt, J Frankle arXiv preprint arXiv:2303.06480, 2023 | 5 | 2023 |
Reduce, reuse, recycle: Improving training efficiency with distillation C Blakeney, JZ Forde, J Frankle, Z Zong, ML Leavitt arXiv preprint arXiv:2211.00683, 2022 | 5 | 2022 |
Neuronal activation sequences in lateral prefrontal cortex encode visuospatial working memory during virtual navigation A Busch, M Roussy, R Luna, ML Leavitt, MH Mofrad, RA Gulli, B Corrigan, ... Nature Communications 15 (1), 4471, 2024 | 4 | 2024 |
On the special role of class-selective neurons in early training O Ranadive, N Thakurdesai, AS Morcos, M Leavitt, S Deny arXiv preprint arXiv:2305.17409, 2023 | 2 | 2023 |
Dynamic masking rate schedules for mlm pretraining Z Ankner, N Saphra, D Blalock, J Frankle, ML Leavitt arXiv preprint arXiv:2305.15096, 2023 | 2 | 2023 |
Composer: A PyTorch Library for Efficient Neural Network Training H Tang, R Rahman, M Patel, M Nadeem, A Venigalla, L Seguin, ... https://github.com/mosaicml/composer, 2021 | 2 | 2021 |