2024
Scalable watermarking for identifying large language model outputs.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Nat., October, 2024
Evaluating Model Bias Requires Characterizing its Mistakes.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
2023
Generative models improve fairness of medical classifiers under distribution shifts.
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2023
Differentially Private Diffusion Models Generate Useful Synthetic Images.
CoRR, 2023
Benchmarking Robustness to Adversarial Image Obfuscations.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Revisiting adapters with adversarial training.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
2022
Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning.
CoRR, 2022
Robustness of Epinets against Distributional Shifts.
CoRR, 2022
Competition-Level Code Generation with AlphaCode.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2022
Hindering Adversarial Attacks with Implicit Neural Representations.
Proceedings of the International Conference on Machine Learning, 2022
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses.
Proceedings of the International Conference on Machine Learning, 2022
A Fine-Grained Analysis on Distribution Shift.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Defending Against Image Corruptions Through Adversarial Augmentations.
Proceedings of the Tenth International Conference on Learning Representations, 2022
2021
Challenges of real-world reinforcement learning: definitions, benchmarks and analysis.
Mach. Learn., 2021
An Empirical Investigation of Learning from Biased Toxicity Labels.
CoRR, 2021
A Closer Look at the Adversarial Robustness of Information Bottleneck Models.
CoRR, 2021
Fixing Data Augmentation to Improve Adversarial Robustness.
CoRR, 2021
Verifying Probabilistic Specifications with Functional Lagrangians.
CoRR, 2021
Data Augmentation Can Improve Robustness.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Improving Robustness using Generated Data.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Self-supervised Adversarial Robustness for the Low-label, High-data Regime.
Proceedings of the 9th International Conference on Learning Representations, 2021
2020
Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples.
CoRR, 2020
An empirical investigation of the challenges of real-world reinforcement learning.
CoRR, 2020
The Autoencoding Variational Autoencoder.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Towards Stable and Efficient Training of Verifiably Robust Neural Networks.
Proceedings of the 8th International Conference on Learning Representations, 2020
Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control.
Proceedings of the 8th International Conference on Learning Representations, 2020
Towards Verified Robustness under Text Deletion Interventions.
Proceedings of the 8th International Conference on Learning Representations, 2020
A Framework for robustness Certification of Smoothed Classifiers using F-Divergences.
Proceedings of the 8th International Conference on Learning Representations, 2020
Towards Robust Image Classification Using Sequential Attention Models.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
2019
An Alternative Surrogate Loss for PGD-based Adversarial Testing.
CoRR, 2019
Efficient Neural Network Verification with Exactness Characterization.
Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, 2019
Adversarial Robustness through Local Linearization.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
A Dual Approach to Verify and Train Deep Networks.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems.
Proceedings of the 36th International Conference on Machine Learning, 2019
Verification of Non-Linear Specifications for Neural Networks.
Proceedings of the 7th International Conference on Learning Representations, 2019
Beyond Greedy Ranking: Slate Optimization via List-CVAE.
Proceedings of the 7th International Conference on Learning Representations, 2019
Scalable Verified Training for Provably Robust Image Classification.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation.
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019
2018
On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models.
CoRR, 2018
Learning from Delayed Outcomes with Intermediate Observations.
CoRR, 2018
Training verified learners with learned verifiers.
CoRR, 2018
Optimizing Slate Recommendations via Slate-CVAE.
CoRR, 2018
A Dual Approach to Scalable Verification of Deep Networks.
Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, 2018
2013
A Framework for Graph-Based Distributed Rendezvous of Nonholonomic Multi-Robot Systems.
PhD thesis, 2013
2012
A new collision warning system for lead vehicles in rear-end collisions.
Proceedings of the 2012 IEEE Intelligent Vehicles Symposium, 2012
Real-Time Optimized Rendezvous on Nonholonomic Resource-Constrained Robots.
Proceedings of the Experimental Robotics, 2012
Real-time optimization of trajectories that guarantee the rendezvous of mobile robots.
Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012
2011
Two-phase online calibration for infrared-based inter-robot positioning modules.
Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
Bayesian rendezvous for distributed robotic systems.
Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
2010
A realistic simulator for the design and evaluation of intelligent vehicles.
Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems, 2010
Local graph-based distributed control for safe highway platooning.
Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010
Graph based distributed control of non-holonomic vehicles endowed with local positioning information engaged in escorting missions.
Proceedings of the IEEE International Conference on Robotics and Automation, 2010
2009
Graph-based distributed control for non-holonomic vehicles engaged in a reconfiguration task using local positioning information.
Proceedings of the 2nd International ICST Conference on Robot Communication and Coordination, 2009