David Krueger

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 64

Top Topics

Reinforcement Learning

Top Venues

Publications

Stephen Casper, Carson Ezell, Charlotte Siegmann, Noam Kolt, Taylor Lynn Curtis, Benjamin Bucknall, Andreas A. Haupt, Kevin Wei, Jérémy Scheurer, Marius Hobbhahn, Lee Sharkey, Satyapriya Krishna, Marvin Von Hagen, Silas Alberti, Alan Chan, Qinyi Sun, Michael Gerovitch, David Bau, Max Tegmark, David Krueger, Dylan Hadfield-Menell
Black-Box Access is Insufficient for Rigorous AI Audits. FAccT (2024)
Stephen Casper, Carson Ezell, Charlotte Siegmann, Noam Kolt, Taylor Lynn Curtis, Benjamin Bucknall, Andreas Alexander Haupt, Kevin Wei, Jérémy Scheurer, Marius Hobbhahn, Lee Sharkey, Satyapriya Krishna, Marvin Von Hagen, Silas Alberti, Alan Chan, Qinyi Sun, Michael Gerovitch, David Bau, Max Tegmark, David Krueger, Dylan Hadfield-Menell
Black-Box Access is Insufficient for Rigorous AI Audits. CoRR (2024)
Alan Chan, Carson Ezell, Max Kaufmann, Kevin Wei, Lewis Hammond, Herbie Bradley, Emma Bluemke, Nitarshan Rajkumar, David Krueger, Noam Kolt, Lennart Heim, Markus Anderljung
Visibility into AI Agents. FAccT (2024)
Alan Chan, Noam Kolt, Peter Wills, Usman Anwar, Christian Schröder de Witt, Nitarshan Rajkumar, Lewis Hammond, David Krueger, Lennart Heim, Markus Anderljung
IDs for AI Systems. CoRR (2024)
Akash R. Wasil, Joshua Clymer, David Krueger, Emily Dardaman, Simeon Campos, Evan R. Murphy
Affirmative safety: An approach to risk management for high-risk AI. CoRR (2024)
Alan Chan, Carson Ezell, Max Kaufmann, Kevin Wei, Lewis Hammond, Herbie Bradley, Emma Bluemke, Nitarshan Rajkumar, David Krueger, Noam Kolt, Lennart Heim, Markus Anderljung
Visibility into AI Agents. CoRR (2024)
Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L. Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, José Hernández-Orallo, Lewis Hammond, Eric J. Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak, Heidi Zhang, Ruiqi Zhong, Seán Ó hÉigeartaigh, Gabriel Recchia, Giulio Corsi, Alan Chan, Markus Anderljung, Lilian Edwards, Yoshua Bengio, Danqi Chen, Samuel Albanie, Tegan Maharaj, Jakob N. Foerster, Florian Tramèr, He He, Atoosa Kasirzadeh, Yejin Choi, David Krueger
Foundational Challenges in Assuring Alignment and Safety of Large Language Models. CoRR (2024)
Lukas Fluri, Leon Lang, Alessandro Abate, Patrick Forré, David Krueger, Joar Skalse
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret. CoRR (2024)
James Urquhart Allingham, Bruno Kacper Mlodozeniec, Shreyas Padhy, Javier Antorán, David Krueger, Richard E. Turner, Eric T. Nalisnick, José Miguel Hernández-Lobato
A Generative Model of Symmetry Transformations. CoRR (2024)
Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, David Krueger
Stress-Testing Capability Elicitation With Password-Locked Models. CoRR (2024)
Joshua Clymer, Nick Gabrieli, David Krueger, Thomas Larsen
Safety Cases: How to Justify the Safety of Advanced AI Systems. CoRR (2024)
Micah Carroll, Alan Chan, Henry Ashton, David Krueger
Characterizing Manipulation from AI Systems. EAAMO (2023)
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Tong Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. Trans. Mach. Learn. Res. 2023 (2023)
Dmitrii Krasheninnikov, Egor Krasheninnikov, Bruno Mlodozeniec, David Krueger
Meta- (out-of-context) learning in neural networks. CoRR (2023)
Alan Chan, Rebecca Salganik, Alva Markelius, Chris Pang, Nitarshan Rajkumar, Dmitrii Krasheninnikov, Lauro Langosco, Zhonghao He, Yawen Duan, Micah Carroll, Michelle Lin, Alex Mayhew, Katherine Collins, Maryam Molamohammadi, John Burden, Wanru Zhao, Shalaleh Rismani, Konstantinos Voudouris, Umang Bhatt, Adrian Weller, David Krueger, Tegan Maharaj
Harms from Increasingly Agentic Algorithmic Systems. FAccT (2023)
Cindy Wu, Ekdeep Singh Lubana, Bruno Kacper Mlodozeniec, Robert Kirk, David Krueger
What Mechanisms Does Knowledge Distillation Distill? UniReps (2023)
Yoshua Bengio, Geoffrey E. Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian K. Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atilim Günes Baydin, Sheila McIlraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca D. Dragan, Philip H. S. Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann
Managing AI Risks in an Era of Rapid Progress. CoRR (2023)
Shoaib Ahmed Siddiqui, David Krueger, Thomas M. Breuel
Investigating the Nature of 3D Generalization in Deep Neural Networks. CoRR (2023)
Ekdeep Singh Lubana, Eric J. Bigelow, Robert P. Dick, David Krueger, Hidenori Tanaka
Mechanistic Mode Connectivity. ICML (2023)
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. CoRR (2023)
Stephen Chung, Ivan Anokhin, David Krueger
Thinker: Learning to Plan and Act. CoRR (2023)
Alan Chan, Ben Bucknall, Herbie Bradley, David Krueger
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models. CoRR (2023)
Thomas Coste, Usman Anwar, Robert Kirk, David Krueger
Reward Model Ensembles Help Mitigate Overoptimization. CoRR (2023)
Shoaib Ahmed Siddiqui, Nitarshan Rajkumar, Tegan Maharaj, David Krueger, Sara Hooker
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics. ICLR (2023)
Alan Chan, Rebecca Salganik, Alva Markelius, Chris Pang, Nitarshan Rajkumar, Dmitrii Krasheninnikov, Lauro Langosco, Zhonghao He, Yawen Duan, Micah Carroll, Michelle Lin, Alex Mayhew, Katherine Collins, Maryam Molamohammadi, John Burden, Wanru Zhao, Shalaleh Rismani, Konstantinos Voudouris, Umang Bhatt, Adrian Weller, David Krueger, Tegan Maharaj
Harms from Increasingly Agentic Algorithmic Systems. CoRR (2023)
Micah Carroll, Alan Chan, Henry Ashton, David Krueger
Characterizing Manipulation from AI Systems. CoRR (2023)
Xander Davies, Lauro Langosco, David Krueger
Unifying Grokking and Double Descent. CoRR (2023)
Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger
Broken Neural Scaling Laws. ICLR (2023)
Stephen Chung, Ivan Anokhin, David Krueger
Thinker: Learning to Plan and Act. NeurIPS (2023)
Lev McKinney, Yawen Duan, David Krueger, Adam Gleave
On The Fragility of Learned Reward Functions. CoRR (2023)
Shoaib Ahmed Siddiqui, David Krueger, Yann LeCun, Stéphane Deny
Blockwise Self-Supervised Learning at Scale. CoRR (2023)
Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger
Broken Neural Scaling Laws. CoRR (2022)
Joar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov, David Krueger
Defining and Characterizing Reward Hacking. CoRR (2022)
Shoaib Ahmed Siddiqui, Nitarshan Rajkumar, Tegan Maharaj, David Krueger, Sara Hooker
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics. CoRR (2022)
Ekdeep Singh Lubana, Eric J. Bigelow, Robert P. Dick, David Krueger, Hidenori Tanaka
Mechanistic Mode Connectivity. CoRR (2022)
Lauro Langosco di Langosco, Jack Koch, Lee D. Sharkey, Jacob Pfau, David Krueger
Goal Misgeneralization in Deep Reinforcement Learning. ICML (2022)
Adam Ibrahim, Charles Guille-Escuret, Ioannis Mitliagkas, Irina Rish, David Krueger, Pouya Bashivan
Towards Out-of-Distribution Adversarial Robustness. CoRR (2022)
Alan Clark, Shoaib Ahmed Siddiqui, Robert Kirk, Usman Anwar, Stephen Chung, David Krueger
Domain Generalization for Robust Model-Based Offline Reinforcement Learning. CoRR (2022)
Joar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov, David Krueger
Defining and Characterizing Reward Gaming. NeurIPS (2022)
David Krueger, Ethan Caballero, Jörn-Henrik Jacobsen, Amy Zhang, Jonathan Binas, Dinghuai Zhang, Rémi Le Priol, Aaron C. Courville
Out-of-Distribution Generalization via Risk Extrapolation (REx). ICML (2021)
Enoch Tetteh, Joseph D. Viviano, Yoshua Bengio, David Krueger, Joseph Paul Cohen
Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models. CoRR (2021)
Shahar Avin, Haydn Belfield, Miles Brundage, Gretchen Krueger, Jasmine Wang, Adrian Weller, Markus Anderljung, Igor Krawczuk, David Krueger, Jonathan Lebensold, Tegan Maharaj, Noa Zilberman
Filling gaps in trustworthy development of AI. CoRR (2021)
Miles Brundage, Shahar Avin, Jasmine Wang, Haydn Belfield, Gretchen Krueger, Gillian K. Hadfield, Heidy Khlaaf, Jingying Yang, Helen Toner, Ruth Fong, Tegan Maharaj, Pang Wei Koh, Sara Hooker, Jade Leung, Andrew Trask, Emma Bluemke, Jonathan Lebensold, Cullen O'Keefe, Mark Koren, Théo Ryffel, J. B. Rubinovitz, Tamay Besiroglu, Federica Carugati, Jack Clark, Peter Eckersley, Sarah de Haas, Maritza Johnson, Ben Laurie, Alex Ingerman, Igor Krawczuk, Amanda Askell, Rosario Cammarota, Andrew Lohn, David Krueger, Charlotte Stix, Peter Henderson, Logan Graham, Carina Prunkl, Bianca Martin, Elizabeth Seger, Noa Zilberman, Seán Ó hÉigeartaigh, Frens Kroeger, Girish Sastry, Rebecca Kagan, Adrian Weller, Brian Tse, Elizabeth Barnes, Allan Dafoe, Paul Scharre, Ariel Herbert-Voss, Martijn Rasser, Shagun Sodhani, Carrick Flynn, Thomas Krendl Gilbert, Lisa Dyer, Saif Khan, Yoshua Bengio, Markus Anderljung
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims. CoRR (2020)
David Krueger, Ethan Caballero, Jörn-Henrik Jacobsen, Amy Zhang, Jonathan Binas, Rémi Le Priol, Aaron C. Courville
Out-of-Distribution Generalization via Risk Extrapolation (REx). CoRR (2020)
David Krueger, Tegan Maharaj, Jan Leike
Hidden Incentives for Auto-Induced Distributional Shift. CoRR (2020)
Andrew Critch, David Krueger
AI Research Considerations for Human Existential Safety (ARCHES). CoRR (2020)
David Krueger, Jan Leike, Owain Evans, John Salvatier
Active Reinforcement Learning: Observing Rewards at a Cost. CoRR (2020)
Alexandre Lacoste, Boris N. Oreshkin, Wonchang Chung, Thomas Boquet, Negar Rostamzadeh, David Krueger
Uncertainty in Multitask Transfer Learning. CoRR (2018)
Chin-Wei Huang, David Krueger, Alexandre Lacoste, Aaron C. Courville
Neural Autoregressive Flows. CoRR (2018)
Joel Ruben Antony Moniz, David Krueger
Nested LSTMs. CoRR (2018)
Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg
Scalable agent alignment via reward modeling: a research direction. CoRR (2018)
Chin-Wei Huang, David Krueger, Alexandre Lacoste, Aaron C. Courville
Neural Autoregressive Flows. ICML (2018)
Devansh Arpit, Stanislaw Jastrzebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron C. Courville, Yoshua Bengio, Simon Lacoste-Julien
A Closer Look at Memorization in Deep Networks. ICML (2017)
David Krueger, Chin-Wei Huang, Riashat Islam, Ryan Turner, Alexandre Lacoste, Aaron C. Courville
Bayesian Hypernetworks. CoRR (2017)
David Krueger, Nicolas Ballas, Stanislaw Jastrzebski, Devansh Arpit, Maxinder S. Kanwal, Tegan Maharaj, Emmanuel Bengio, Asja Fischer, Aaron C. Courville
Deep Nets Don't Learn via Memorization. ICLR (Workshop) (2017)
Alexandre Lacoste, Thomas Boquet, Negar Rostamzadeh, Boris N. Oreshkin, Wonchang Chung, David Krueger
Deep Prior. CoRR (2017)
Devansh Arpit, Stanislaw Jastrzebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron C. Courville, Yoshua Bengio, Simon Lacoste-Julien
A Closer Look at Memorization in Deep Networks. CoRR (2017)
David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Aaron C. Courville, Christopher J. Pal
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations. ICLR (Poster) (2017)
Joel Ruben Antony Moniz, David Krueger
Nested LSTMs. ACML (2017)
David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Aaron C. Courville, Chris Pal
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations. CoRR (2016)
David Krueger, Roland Memisevic
Regularizing RNNs by Stabilizing Activations. ICLR (2016)
Philip Bachman, David Krueger, Doina Precup
Testing Visual Attention in Dynamic Environments. CoRR (2015)
Roland Memisevic, Kishore Reddy Konda, David Krueger
Zero-bias autoencoders and the benefits of co-adapting features. ICLR (Poster) (2015)
Laurent Dinh, David Krueger, Yoshua Bengio
NICE: Non-linear Independent Components Estimation. ICLR (Workshop) (2015)