Chris Cundy

29 papers A* 4A 2Journal 21Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes.
CoRR
Mohammad Taufeeque, Stefan Heimersheim, Adam Gleave, Chris Cundy
2025 J jnl
AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations.
CoRR
Dillon Bowen, Ann-Kathrin Dombrowski, Adam Gleave, Chris Cundy
2025 J jnl
Auditing Games for Sandbagging.
CoRR
Jordan Taylor, Sid Black, Dillon Bowen, Thomas Read, Satvik Golechha, Alex Zelenka-Martin, Oliver Makins, Connor Kissane, Kola Ayonrinde, Jacob Merizian, Samuel Marks, Chris Cundy, Joseph Isaac Bloom
2025 J jnl
Bare Minimum Mitigations for Autonomous AI Development.
CoRR
Joshua Clymer, Isabella Duan, Chris Cundy, Yawen Duan, Fynn Heide, Chaochao Lu, Sören Mindermann, Conor McGurk, Xudong Pan, Saad Siddiqui, Jingren Wang, Min Yang, Xianyuan Zhan
2025 J jnl
KGGen: Extracting Knowledge Graphs from Plain Text with Language Models.
CoRR
Belinda Mo, Kyssen Yu, Joshua Kazdan, Proud Mpala, Lisa Yu, Chris Cundy, Charilaos I. Kanatsoulis, Sanmi Koyejo
2025 J jnl
No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data.
CoRR
Joshua Kazdan, Lisa Yu, Rylan Schaeffer, Chris Cundy, Sanmi Koyejo, Dvijotham Krishnamurthy
2025 J jnl
Preference Learning with Lie Detectors can Induce Honesty or Evasion.
CoRR
Chris Cundy, Adam Gleave
2025 J jnl
Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF.
CoRR
Syrine Belakaria, Joshua Kazdan, Charles Marx, Chris Cundy, Willie Neiswanger, Sanmi Koyejo, Barbara E. Engelhardt, Stefano Ermon
2025 J jnl
The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models.
CoRR
Ann-Kathrin Dombrowski, Dillon Bowen, Adam Gleave, Chris Cundy
2024 J jnl
On the Opportunities and Challenges of Foundation Models for GeoAI (Vision Paper).
ACM Trans. Spatial Algorithms Syst.
Gengchen Mai, Weiming Huang, Jin Sun, Suhang Song, Deepak Mishra, Ninghao Liu, Song Gao, Tianming Liu, Gao Cong, Yingjie Hu, Chris Cundy, Ziyuan Li, Rui Zhu, Ni Lao
2024 A conf
Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients.
AISTATS
Chris Cundy, Rishi Desai, Stefano Ermon
2024 A* conf
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking.
ICLR
Chris Cundy, Stefano Ermon
2023 J jnl
Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages.
CoRR
Yingjie Hu, Gengchen Mai, Chris Cundy, Kristy Choi, Ni Lao, Wei Liu, Gaurish Lakhanpal, Ryan Zhenqi Zhou, Kenneth Joseph
2023 J jnl
Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages.
Int. J. Geogr. Inf. Sci.
Yingjie Hu, Gengchen Mai, Chris Cundy, Kristy Choi, Ni Lao, Wei Liu, Gaurish Lakhanpal, Ryan Zhenqi Zhou, Kenneth Joseph
2023 A* conf
Neural Networks and the Chomsky Hierarchy.
ICLR
Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Chris Cundy, Marcus Hutter, Shane Legg, Joel Veness, Pedro A. Ortega
2023 J jnl
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence.
CoRR
Gengchen Mai, Weiming Huang, Jin Sun, Suhang Song, Deepak Mishra, Ninghao Liu, Song Gao, Tianming Liu, Gao Cong, Yingjie Hu, Chris Cundy, Ziyuan Li, Rui Zhu, Ni Lao
2023 J jnl
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking.
CoRR
Chris Cundy, Stefano Ermon
2022 J jnl
Beyond Bayes-optimality: meta-learning what you know you don't know.
CoRR
Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Tim Genewein, Elliot Catt, Kevin Li, Anian Ruoss, Chris Cundy, Joel Veness, Jane X. Wang, Marcus Hutter, Christopher Summerfield, Shane Legg, Pedro A. Ortega
2022 J jnl
LMPriors: Pre-Trained Language Models as Task-Specific Priors.
CoRR
Kristy Choi, Chris Cundy, Sanjari Srivastava, Stefano Ermon
2022 — conf
Towards a foundation model for geospatial artificial intelligence (vision paper).
SIGSPATIAL/GIS
Gengchen Mai, Chris Cundy, Kristy Choi, Yingjie Hu, Ni Lao, Stefano Ermon
2021 A* conf
BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery.
NeurIPS
Chris Cundy, Aditya Grover, Stefano Ermon
2021 J jnl
BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery.
CoRR
Chris Cundy, Aditya Grover, Stefano Ermon
2021 A* conf
IQ-Learn: Inverse soft-Q Learning for Imitation.
NeurIPS
Divyansh Garg, Shuvam Chakraborty, Chris Cundy, Jiaming Song, Stefano Ermon
2021 J jnl
IQ-Learn: Inverse soft-Q Learning for Imitation.
CoRR
Divyansh Garg, Shuvam Chakraborty, Chris Cundy, Jiaming Song, Stefano Ermon
2020 A conf
Flexible Approximate Inference via Stratified Normalizing Flows.
UAI
Chris Cundy, Stefano Ermon
2020 J jnl
Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients.
CoRR
Chris Cundy, Stefano Ermon
2018 J jnl
Exploring Hierarchy-Aware Inverse Reinforcement Learning.
CoRR
Chris Cundy, Daniel Filan
2018 — conf
Parallelizing Linear Recurrent Neural Nets Over Sequence Length.
ICLR (Poster)
Eric Martin, Chris Cundy
2017 J jnl
Parallelizing Linear Recurrent Neural Nets Over Sequence Length.
CoRR
Eric Martin, Chris Cundy