Lawrence Chan

29 papers A* 7Journal 19Unranked 3
YearRankTypeTitle / Venue / Authors
2025 J jnl
HCAST: Human-Calibrated Autonomy Software Tasks.
CoRR
David Rein, Joel Becker, Amy Deng, Seraphina Nix, Chris Canal, Daniel O'Connel, Pip Arnott, Ryan Bloom, Thomas Broadley, Katharyn Garcia, Brian Goodrich, Max Hasin, Sami Jawhar, Megan Kinniment, Thomas Kwa, Aron Lajko, Nate Rush, Lucas Jun Koba Sato, Sydney von Arx, Ben West, Lawrence Chan, Elizabeth Barnes
2025 J jnl
Measuring AI Ability to Complete Long Tasks.
CoRR
Thomas Kwa, Ben West, Joel Becker, Amy Deng, Katharyn Garcia, Max Hasin, Sami Jawhar, Megan Kinniment, Nate Rush, Sydney von Arx, Ryan Bloom, Thomas Broadley, Haoxing Du, Brian Goodrich, Nikola Jurkovic, Luke Harold Miles, Seraphina Nix, Tao Lin, Neev Parikh, David Rein, Lucas Jun Koba Sato, Hjalmar Wijk, Daniel M. Ziegler, Elizabeth Barnes, Lawrence Chan
2025 A* conf
RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts.
ICML
Hjalmar Wijk, Tao Roa Lin, Joel Becker, Sami Jawhar, Neev Parikh, Thomas Broadley, Lawrence Chan, Michael Chen, Joshua Clymer, Jai Dhyani, Elena Ericheva, Katharyn Garcia, Brian Goodrich, Nikola Jurkovic, Megan Kinniment, Aron Lajko, Seraphina Nix, Lucas Jun Koba Sato, William Saunders, Maksym Taran, Ben West, Elizabeth Barnes
2024 A* conf
Compact Proofs of Model Performance via Mechanistic Interpretability.
NeurIPS
Jason Gross, Rajashree Agrawal, Thomas Kwa, Euan Ong, Chun Hei Yip, Alex Gibson, Soufiane Noubir, Lawrence Chan
2024 J jnl
Compact Proofs of Model Performance via Mechanistic Interpretability.
CoRR
Jason Gross, Rajashree Agrawal, Thomas Kwa, Euan Ong, Chun Hei Yip, Alex Gibson, Soufiane Noubir, Lawrence Chan
2024 J jnl
Language Models Are Better Than Humans at Next-token Prediction.
Trans. Mach. Learn. Res.
Buck Shlegeris, Fabien Roger, Lawrence Chan, Euan McLean
2024 J jnl
Mathematical Models of Computation in Superposition.
CoRR
Kaarel Hänni, Jake Mendel, Dmitry Vaintrob, Lawrence Chan
2024 J jnl
Modular addition without black-boxes: Compressing explanations of MLPs that compute numerical integration.
CoRR
Chun Hei Yip, Rajashree Agrawal, Lawrence Chan, Jason Gross
2024 J jnl
RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts.
CoRR
Hjalmar Wijk, Tao Lin, Joel Becker, Sami Jawhar, Neev Parikh, Thomas Broadley, Lawrence Chan, Michael Chen, Joshua Clymer, Jai Dhyani, Elena Ericheva, Katharyn Garcia, Brian Goodrich, Nikola Jurkovic, Megan Kinniment, Aron Lajko, Seraphina Nix, Lucas Sato, William Saunders, Maksym Taran, Ben West, Elizabeth Barnes
2024 A* conf
The Alignment Problem from a Deep Learning Perspective.
ICLR
Richard Ngo, Lawrence Chan, Sören Mindermann
2023 J jnl
A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations.
CoRR
Bilal Chughtai, Lawrence Chan, Neel Nanda
2023 A* conf
A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations.
ICML
Bilal Chughtai, Lawrence Chan, Neel Nanda
2023 J jnl
Evaluating Language-Model Agents on Realistic Autonomous Tasks.
CoRR
Megan Kinniment, Lucas Jun Koba Sato, Haoxing Du, Brian Goodrich, Max Hasin, Lawrence Chan, Luke Harold Miles, Tao Roa Lin, Hjalmar Wijk, Joel Burget, Aaron Ho, Elizabeth Barnes, Paul F. Christiano
2023 A* conf
Progress measures for grokking via mechanistic interpretability.
ICLR
Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
2023 J jnl
Progress measures for grokking via mechanistic interpretability.
CoRR
Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
2022 J jnl
Adversarial Training for High-Stakes Reliability.
CoRR
Daniel M. Ziegler, Seraphina Nix, Lawrence Chan, Tim Bauman, Peter Schmidt-Nielsen, Tao Lin, Adam Scherlis, Noa Nabeshima, Ben Weinstein-Raun, Daniel de Haas, Buck Shlegeris, Nate Thomas
2022 A* conf
Adversarial training for high-stakes reliability.
NeurIPS
Daniel M. Ziegler, Seraphina Nix, Lawrence Chan, Tim Bauman, Peter Schmidt-Nielsen, Tao Lin, Adam Scherlis, Noa Nabeshima, Ben Weinstein-Raun, Daniel de Haas, Buck Shlegeris, Nate Thomas
2022 J jnl
Language models are better than humans at next-token prediction.
CoRR
Buck Shlegeris, Fabien Roger, Lawrence Chan, Euan McLean
2021 — conf
A Fast-Processing Pipeline for Three-dimensional Visualization of Acute Ischemic Stroke lesion topography.
BIBM
Huiling Shao, Lawrence Chan, Fiona Chen, Qilin Ma, Zhiyu Shao, Heng Du
2021 J jnl
Human irrationality: both bad and good for reward inference.
CoRR
Lawrence Chan, Andrew Critch, Anca D. Dragan
2021 — conf
Optimal Cost Design for Model Predictive Control.
L4DC
Avik Jain, Lawrence Chan, Daniel S. Brown, Anca D. Dragan
2021 J jnl
Optimal Cost Design for Model Predictive Control.
CoRR
Avik Jain, Lawrence Chan, Daniel S. Brown, Anca D. Dragan
2020 J jnl
Accounting for Human Learning when Inferring Human Preferences.
CoRR
Harry Giles, Lawrence Chan
2019 A* conf
The Assistive Multi-Armed Bandit.
HRI
Lawrence Chan, Dylan Hadfield-Menell, Siddhartha S. Srinivasa, Anca D. Dragan
2019 J jnl
The Assistive Multi-Armed Bandit.
CoRR
Lawrence Chan, Dylan Hadfield-Menell, Siddhartha S. Srinivasa, Anca D. Dragan
2012 — conf
Clinical Decision Support using Traditional Chinese Medicine (TCM) Ontology and Text Similarity.
Nursing Informatics
Meyrick Chow, Lawrence Chan
2010 J jnl
Development and evaluation of a compartmental picture archiving and communications system model for integration and visualization of multidisciplinary biomedical data to facilitate student learning in an integrative health clinic.
Comput. Educ.
Meyrick Chow, Lawrence Chan
2007 J jnl
International Internet2 connectivity and performance in medical imaging applications: Bridging the Americas to Asia.
J. High Speed Networks
Brent J. Liu, Zheng Zhou, Marco A. Gutierrez, Jorge Documet, Lawrence Chan, H. K. Huang
2007 J jnl
The role of a Data Grid in worldwide imaging-based clinical trials.
J. High Speed Networks
Zheng Zhou, Marco A. Gutierrez, Jorge Documet, Lawrence Chan, H. K. Huang, Brent J. Liu