Scott Emmons

41 papers A* 11Journal 28Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies.
CoRR
Miles Brundage, Noemi Dreksler, Aidan Homewood, Sean McGregor, Patricia Paskov, Conrad Stosz, Girish Sastry, A. Feder Cooper, George Balston, Steven Adler, Stephen Casper, Markus Anderljung, Grace W. Lindsay, Sören Mindermann, Vasilios Mavroudis, Ben Bucknall, Charlotte Stix, Jonas Freund, Lorenzo Pacchiardi, José Hernández-Orallo, Matteo Pistillo, Michael Chen, Chris Painter, Dean W. Ball, Cullen O'Keefe, Gabriel Weil, Ben Harack, Graeme Finley, Ryan Hassan, Scott Emmons, Charles Foster, Anka Reuel, Bri Treece, Yoshua Bengio, Daniel Reti, Rishi Bommasani, Cristian Trout, Ali Shahin Shamsabadi, Rajiv Dattani, Adrian Weller, Robert Trager, Jaime Sevilla, Lauren Wagner, Lisa Soder, Ketan Ramakrishnan, Henry Papadatos, Malcolm Murray, Ryan Tovcimak
2025 J jnl
A Pragmatic Way to Measure Chain-of-Thought Monitorability.
CoRR
Scott Emmons, Roland S. Zimmermann, David K. Elson, Rohin Shah
2025 J jnl
An Approach to Technical AGI Safety and Security.
CoRR
Rohin Shah, Alex Irpan, Alexander Matt Turner, Anna Wang, Arthur Conmy, David Lindner, Jonah Brown-Cohen, Lewis Ho, Neel Nanda, Raluca Ada Popa, Rishub Jain, Rory Greig, Samuel Albanie, Scott Emmons, Sebastian Farquhar, Sébastien Krier, Senthooran Rajamanoharan, Sophie Bridgers, Tobi Ijitoye, Tom Everitt, Victoria Krakovna, Vikrant Varma, Vladimir Mikulik, Zachary Kenton, Dave Orr, Shane Legg, Noah D. Goodman, Allan Dafoe, Four Flynn, Anca D. Dragan
2025 J jnl
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.
CoRR
Tomek Korbak, Mikita Balesni, Elizabeth Barnes, Yoshua Bengio, Joe Benton, Joseph Bloom, Mark Chen, Alan Cooney, Allan Dafoe, Anca D. Dragan, Scott Emmons, Owain Evans, David Farhi, Ryan Greenblatt, Dan Hendrycks, Marius Hobbhahn, Evan Hubinger, Geoffrey Irving, Erik Jenner, Daniel Kokotajlo, Victoria Krakovna, Shane Legg, David Lindner, David Luan, Aleksander Madry, Julian Michael, Neel Nanda, Dave Orr, Jakub Pachocki, Ethan Perez, Mary Phuong, Fabien Roger, Joshua Saxe, Buck Shlegeris, Martín Soto, Eric Steinberger, Jasmine Wang, Wojciech Zaremba, Bowen Baker, Rohin Shah, Vladimir Mikulik
2025 A* conf
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models.
ICLR
Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristóbal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, Tony Tong Wang, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez
2025 J jnl
Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors.
CoRR
Max McGuinness, Alex Serrano, Luke Bailey, Scott Emmons
2025 A* conf
Observation Interference in Partially Observable Assistance Games.
ICML
Scott Emmons, Caspar Oesterheld, Vincent Conitzer, Stuart Russell
2025 A* conf
The Partially Observable Off-Switch Game.
AAAI
Andrew Garber, Rohan Subramani, Linus Luu, Mark Bedaywi, Stuart Russell, Scott Emmons
2025 J jnl
When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors.
CoRR
Scott Emmons, Erik Jenner, David K. Elson, Rif A. Saurous, Senthooran Rajamanoharan, Heng Chen, Irhum Shafkat, Rohin Shah
2024 A* conf
A StrongREJECT for Empty Jailbreaks.
NeurIPS
Alexandra Souly, Qingyuan Lu, Dillon Bowen, Tu Trinh, Elvis Hsieh, Sana Pandey, Pieter Abbeel, Justin Svegliato, Scott Emmons, Olivia Watkins, Sam Toyer
2024 J jnl
A StrongREJECT for Empty Jailbreaks.
CoRR
Alexandra Souly, Qingyuan Lu, Dillon Bowen, Tu Trinh, Elvis Hsieh, Sana Pandey, Pieter Abbeel, Justin Svegliato, Scott Emmons, Olivia Watkins, Sam Toyer
2024 A* conf
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network.
NeurIPS
Erik Jenner, Shreyas Kapur, Vasil Georgiev, Cameron Allen, Scott Emmons, Stuart J. Russell
2024 J jnl
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network.
CoRR
Erik Jenner, Shreyas Kapur, Vasil Georgiev, Cameron Allen, Scott Emmons, Stuart Russell
2024 A* conf
Image Hijacks: Adversarial Images can Control Generative Models at Runtime.
ICML
Luke Bailey, Euan Ong, Stuart Russell, Scott Emmons
2024 J jnl
Obfuscated Activations Bypass LLM Latent-Space Defenses.
CoRR
Luke Bailey, Alex Serrano, Abhay Sheshadri, Mikhail Seleznyov, Jordan Taylor, Erik Jenner, Jacob Hilton, Stephen Casper, Carlos Guestrin, Scott Emmons
2024 J jnl
Observation Interference in Partially Observable Assistance Games.
CoRR
Scott Emmons, Caspar Oesterheld, Vincent Conitzer, Stuart Russell
2024 — —
The Alignment Problem Under Partial Observability
Scott Emmons
2024 J jnl
Uncovering Latent Human Wellbeing in Language Model Embeddings.
CoRR
Pedro Freire, ChengCheng Tan, Adam Gleave, Dan Hendrycks, Scott Emmons
2024 J jnl
When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
CoRR
Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristóbal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez
2024 A* conf
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback.
NeurIPS
Leon Lang, Davis Foote, Stuart J. Russell, Anca D. Dragan, Erik Jenner, Scott Emmons
2024 J jnl
When Your AIs Deceive You: Challenges with Partial Observability of Human Evaluators in Reward Learning.
CoRR
Leon Lang, Davis Foote, Stuart Russell, Anca D. Dragan, Erik Jenner, Scott Emmons
2024 J jnl
Will an AI with Private Information Allow Itself to Be Switched Off?
CoRR
Andrew Garber, Rohan Subramani, Linus Luu, Mark Bedaywi, Stuart Russell, Scott Emmons
2023 J jnl
ALMANACS: A Simulatability Benchmark for Language Model Explainability.
CoRR
Edmund Mills, Shiye Su, Stuart Russell, Scott Emmons
2023 J jnl
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark.
CoRR
Alexander Pan, Jun Shern Chan, Andy Zou, Nathaniel Li, Steven Basart, Thomas Woodside, Jonathan Ng, Hanlin Zhang, Scott Emmons, Dan Hendrycks
2023 A* conf
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark.
ICML
Alexander Pan, Jun Shern Chan, Andy Zou, Nathaniel Li, Steven Basart, Thomas Woodside, Hanlin Zhang, Scott Emmons, Dan Hendrycks
2023 J jnl
Image Hijacks: Adversarial Images can Control Generative Models at Runtime.
CoRR
Luke Bailey, Euan Ong, Stuart Russell, Scott Emmons
2022 J jnl
An Empirical Investigation of Representation Learning for Imitation.
CoRR
Xin Chen, Sam Toyer, Cody Wild, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H. Wang, Ping Luo, Stuart Russell, Pieter Abbeel, Rohin Shah
2022 A* conf
For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria.
ICML
Scott Emmons, Caspar Oesterheld, Andrew Critch, Vincent Conitzer, Stuart Russell
2022 J jnl
For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria.
CoRR
Scott Emmons, Caspar Oesterheld, Andrew Critch, Vincent Conitzer, Stuart Russell
2022 A* conf
RvS: What is Essential for Offline RL via Supervised Learning?
ICLR
Scott Emmons, Benjamin Eysenbach, Ilya Kostrikov, Sergey Levine
2022 J jnl
imitation: Clean Imitation Learning Implementations.
CoRR
Adam Gleave, Mohammad Taufeeque, Juan Rocamonde, Erik Jenner, Steven H. Wang, Sam Toyer, Maximilian Ernestus, Nora Belrose, Scott Emmons, Stuart Russell
2021 — conf
An Empirical Investigation of Representation Learning for Imitation.
NeurIPS Datasets and Benchmarks
Cynthia Chen, Xin Chen, Sam Toyer, Cody Wild, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H. Wang, Ping Luo, Stuart Russell, Pieter Abbeel, Rohin Shah
2021 J jnl
RvS: What is Essential for Offline RL via Supervised Learning?
CoRR
Scott Emmons, Benjamin Eysenbach, Ilya Kostrikov, Sergey Levine
2020 A* conf
Sparse Graphical Memory for Robust Planning.
NeurIPS
Scott Emmons, Ajay Jain, Michael Laskin, Thanard Kurutach, Pieter Abbeel, Deepak Pathak
2020 J jnl
Sparse Graphical Memory for Robust Planning.
CoRR
Michael Laskin, Scott Emmons, Ajay Jain, Thanard Kurutach, Pieter Abbeel, Deepak Pathak
2018 J jnl
A Map Equation with Metadata: Varying the Role of Attributes in Community Detection.
CoRR
Scott Emmons, Peter J. Mucha
2018 J jnl
Global Redundancy Resolution via Continuous Pseudoinversion of the Forward Kinematic Map.
IEEE Trans Autom. Sci. Eng.
Kris Hauser, Scott Emmons
2017 J jnl
MOOC visual analytics: Empowering students, teachers, researchers, and platform developers of massively open online courses.
J. Assoc. Inf. Sci. Technol.
Scott Emmons, Robert P. Light, Katy Börner
2017 J jnl
Post-Processing Partitions to Identify Domains of Modularity Optimization.
Algorithms
William H. Weir, Scott Emmons, Ryan Gibson, Dane Taylor, Peter J. Mucha
2017 J jnl
Post-processing partitions to identify domains of modularity optimization.
CoRR
William H. Weir, Scott Emmons, Ryan Gibson, Dane Taylor, Peter J. Mucha
2016 J jnl
Analysis of Network Clustering Algorithms and Cluster Quality Metrics at Scale.
CoRR
Scott Emmons, Stephen G. Kobourov, Mike Gallant, Katy Börner