Urmăriți
Isaac Liao
Titlu
Citat de
Citat de
Anul
Not all language model features are linear
J Engels, EJ Michaud, I Liao, W Gurnee, M Tegmark
arXiv preprint arXiv:2405.14860, 2024
402024
Opening the ai black box: program synthesis via mechanistic interpretability
EJ Michaud, I Liao, V Lad, Z Liu, A Mudide, C Loughridge, ZC Guo, ...
arXiv preprint arXiv:2402.05110, 2024
122024
Not all language model features are linear, 2024
J Engels, I Liao, EJ Michaud, W Gurnee, M Tegmark
URL https://arxiv. org/abs/2405.14860, 0
6
Generating interpretable networks using hypernetworks
I Liao, Z Liu, M Tegmark
arXiv preprint arXiv:2312.03051, 2023
22023
Learning to optimize quasi-Newton methods
I Liao, RR Dangovski, JN Foerster, M Soljačić
arXiv preprint arXiv:2210.06171, 2022
22022
Opening the AI Black Box: Distilling Machine-Learned Algorithms into Code
EJ Michaud, I Liao, V Lad, Z Liu, A Mudide, C Loughridge, ZC Guo, ...
Entropy 26 (12), 1046, 2024
2024
Streamlining Physics Problem Generation to Support Physics Teachers in Using Generative Artificial Intelligence
S El-Adawy, I Liao, V Lad, M Abdelhafez, P Dourmashkin
The Physics Teacher 62 (7), 595-598, 2024
2024
Exploring the integration of AI into Physics Education: Leveraging ChatGPT for Problem Generation
V Lad, I Liao, M Abdelhafez, P Dourmashkin, S El-Adawy
APS April Meeting Abstracts 2024, N00. 061, 2024
2024
Automated Mechanistic Interpretability for Neural Networks
IC Liao
Massachusetts Institute of Technology, 2024
2024
Bayesian Recommendation Systems
IC Liao
Parameter-Efficient Approximation by Exploitation of Sparsity
I Liao
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–11