Chris Cundy

Orcid: 0000-0002-4608-4110

According to our database1, Chris Cundy authored at least 24 papers between 2018 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes.
CoRR, February, 2026

2025
Auditing Games for Sandbagging.
CoRR, December, 2025

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models.
CoRR, July, 2025

Preference Learning with Lie Detectors can Induce Honesty or Evasion.
CoRR, May, 2025

Bare Minimum Mitigations for Autonomous AI Development.
CoRR, April, 2025

Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF.
CoRR, March, 2025

AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations.
CoRR, March, 2025

No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data.
CoRR, February, 2025

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models.
CoRR, February, 2025

2024
On the Opportunities and Challenges of Foundation Models for GeoAI (Vision Paper).
ACM Trans. Spatial Algorithms Syst., June, 2024

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023
Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages.
Int. J. Geogr. Inf. Sci., November, 2023

On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence.
CoRR, 2023

Neural Networks and the Chomsky Hierarchy.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
LMPriors: Pre-Trained Language Models as Task-Specific Priors.
CoRR, 2022

Beyond Bayes-optimality: meta-learning what you know you don't know.
CoRR, 2022

Towards a foundation model for geospatial artificial intelligence (vision paper).
Proceedings of the 30th International Conference on Advances in Geographic Information Systems, 2022

2021
IQ-Learn: Inverse soft-Q Learning for Imitation.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020
Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients.
CoRR, 2020

Flexible Approximate Inference via Stratified Normalizing Flows.
Proceedings of the Thirty-Sixth Conference on Uncertainty in Artificial Intelligence, 2020

2018
Exploring Hierarchy-Aware Inverse Reinforcement Learning.
CoRR, 2018

Parallelizing Linear Recurrent Neural Nets Over Sequence Length.
Proceedings of the 6th International Conference on Learning Representations, 2018


  Loading...