Sledovat
Eric J. Michaud
Eric J. Michaud
Graduate student, MIT
E-mailová adresa ověřena na: mit.edu - Domovská stránka
Název
Citace
Citace
Rok
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ...
TMLR (Outstanding Paper Finalist), 2023
4742023
Towards understanding grokking: An effective theory of representation learning
Z Liu, O Kitouni, NS Nolte, EJ Michaud, M Tegmark, M Williams
NeurIPS 2022 (Oral), 2022
1512022
Omnigrok: Grokking beyond algorithmic data
Z Liu, EJ Michaud, M Tegmark
ICLR 2023 (Spotlight), 2022
1032022
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
S Marks, C Rager, EJ Michaud, Y Belinkov, D Bau, A Mueller
ICLR 2025 (Oral), 2024
822024
The Quantization Model of Neural Scaling
EJ Michaud, Z Liu, U Girit, M Tegmark
NeurIPS 2023, 2023
732023
Not all language model features are one-dimensionally linear
J Engels, EJ Michaud, I Liao, W Gurnee, M Tegmark
ICLR 2025, 2024
40*2024
Precision Machine Learning
EJ Michaud, Z Liu, M Tegmark
Entropy 25 (1), 175, 2022
402022
Understanding Learned Reward Functions
EJ Michaud, A Gleave, S Russell
Deep RL Workshop, NeurIPS 2020, 2020
402020
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
12*2024
Examining the Causal Structures of Deep Neural Networks Using Information Theory
S Marrow, EJ Michaud, E Hoel
Entropy 22 (12), 1429, 2020
10*2020
The Geometry of Concepts: Sparse Autoencoder Feature Structure
Y Li*, EJ Michaud*, DD Baek*, J Engels, X Sun, M Tegmark
arXiv preprint arXiv:2410.19750, 2024
42024
Open Problems in Mechanistic Interpretability
L Sharkey, B Chughtai, J Batson, J Lindsey, J Wu, L Bushnaq, ...
arXiv preprint arXiv:2501.16496, 2025
32025
Efficient Dictionary Learning with Switch Sparse Autoencoders
A Mudide, J Engels, EJ Michaud, M Tegmark, CS de Witt
ICLR 2025, 2024
22024
Survival of the Fittest Representation: A Case Study with Modular Addition
X Delores Ding, ZC Guo, EJ Michaud, Z Liu, M Tegmark
arXiv e-prints, arXiv: 2405.17420, 2024
1*2024
Lunar Opportunities for SETI
EJ Michaud, APV Siemion, J Drew, SP Worden
arXiv preprint arXiv:2009.12689, 2020
12020
Physics of Skill Learning
Z Liu, Y Liu, EJ Michaud, J Gore, M Tegmark
arXiv preprint arXiv:2501.12391, 2025
2025
A Physics of Systems that Learn
EJ Michaud
2024
SETI from the Lunar South Pole
EJ Michaud, APV Siemion, J Drew, SP Worden
2020
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–18