متابعة
Lawrence Chan
Lawrence Chan
PhD Student, UC Berkeley
بريد إلكتروني تم التحقق منه على berkeley.edu
عنوان
عدد مرات الاقتباسات
عدد مرات الاقتباسات
السنة
Progress measures for grokking via mechanistic interpretability‏
N Nanda, L Chan, T Liberum, J Smith, J Steinhardt‏
ICLR 2023, 2023‏
3552023
The alignment problem from a deep learning perspective‏
R Ngo, L Chan, S Mindermann‏
ICLR 2024, 2022‏
209*2022
A toy model of universality: Reverse engineering how networks learn group operations‏
B Chughtai, L Chan, N Nanda‏
ICML 2023, 2023‏
912023
Causal Scrubbing: a method for rigorously testing interpretability hypotheses‏
L Chan, A Garriga-Alonso, N Goldowsky-Dill, R Greenblatt, ...‏
https://www.alignmentforum.org/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a …, 2022‏
642022
The assistive multi-armed bandit‏
L Chan, D Hadfield-Menell, S Srinivasa, A Dragan‏
2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI …, 2019‏
552019
Adversarial Training for High-Stakes Reliability‏
DM Ziegler, S Nix, L Chan, T Bauman, P Schmidt-Nielsen, T Lin, ...‏
NeurIPS 2022, 2022‏
532022
Evaluating Language-Model Agents on Realistic Autonomous Tasks‏
M Kinniment, LJK Sato, H Du, B Goodrich, M Hasin, L Chan, LH Miles, ...‏
https://evals.alignment.org/Evaluating_LMAs_Realistic_Tasks.pdf, 2023‏
382023
Benefits of assistance over reward learning‏
R Shah, P Freire, N Alex, R Freedman, D Krasheninnikov, L Chan, ...‏
362020
Remote corneal suturing wet lab: microsurgical education during the COVID-19 pandemic‏
ND Pasricha, Z Haq, TR Ahmad, L Chan, TK Redd, GD Seitzman, ...‏
Journal of Cataract & Refractive Surgery 46 (12), 1667-1673, 2020‏
332020
Human irrationality: both bad and good for reward inference‏
L Chan, A Critch, A Dragan‏
arXiv preprint arXiv:2111.06956, 2021‏
252021
Optimal cost design for model predictive control‏
A Jain, L Chan, DS Brown, AD Dragan‏
Learning for Dynamics and Control, 1205-1217, 2021‏
232021
The Alignment Problem from a Deep Learning Perspective (2022)‏
R Ngo, L Chan, S Mindermann‏
URL https://arxiv. org/abs/2209.00626.[Accessed: 4th May 2023], 3, 0‏
9
Language models are better than humans at next-token prediction‏
B Shlegeris, F Roger, L Chan, E McLean‏
Transactions of Machine Learning Research (TMLR), 2022‏
82022
Risk factors predicting loss to follow-up, medication noncompliance, and poor visual outcomes among patients with infectious keratitis at a public county hospital‏
JB Lopez, L Chan, M Saifee, S Padmanabhan, M Yung, MF Chan‏
Cornea 42 (9), 1069-1073, 2023‏
62023
Minor tobacco alkaloids as biomarkers to distinguish combusted tobacco use from Electronic Nicotine Delivery Systems use. two new analytical methods‏
P Jacob, L Chan, P Cheung, K Bello, L Yu, G StHelen, NL Benowitz‏
Frontiers in Chemistry 10, 749089, 2022‏
52022
Mathematical models of computation in superposition‏
K Hänni, J Mendel, D Vaintrob, L Chan‏
arXiv preprint arXiv:2408.05451, 2024‏
42024
Compact proofs of model performance via mechanistic interpretability‏
J Gross, R Agrawal, T Kwa, E Ong, CH Yip, A Gibson, S Noubir, L Chan‏
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024‏
22024
Spontaneous hyphema in the setting of COVID-19 pneumonia‏
J Chiang, L Chan, JY Stallworth, MF Chan‏
American Journal of Ophthalmology Case Reports 26, 101447, 2022‏
22022
Re-bench: Evaluating frontier ai r&d capabilities of language model agents against human experts‏
H Wijk, T Lin, J Becker, S Jawhar, N Parikh, T Broadley, L Chan, M Chen, ...‏
arXiv preprint arXiv:2411.15114, 2024‏
12024
Characterization of Polymicrobial and Antibiotic-Resistant Infectious Keratitis in a County Hospital Setting‏
L Chan, JB Lopez, M Saifee, S Padmanabhan, MF Chan, M Yung‏
Cornea open 2 (3), e0016, 2023‏
12023
يتعذر على النظام إجراء العملية في الوقت الحالي. عاود المحاولة لاحقًا.
مقالات 1–20