2025
On the Coexistence and Ensembling of Watermarks.
CoRR, January, 2025
Open Problems in Machine Unlearning for AI Safety.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, January, 2025
2024
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Unanswerable Questions and Ambiguous Prompts.
CoRR, 2024
Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models.
CoRR, 2024
Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models.
CoRR, 2024
Towards Certification of Uncertainty Calibration under Adversarial Attacks.
CoRR, 2024
Risks and Opportunities of Open-Source Generative AI.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Near to Mid-term Risks and Opportunities of Open Source Generative AI.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress.
CoRR, 2024
Can Large Language Model Agents Simulate Human Trust Behaviors?
CoRR, 2024
SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
CoRR, 2024
Can Large Language Model Agents Simulate Human Trust Behavior?
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Efficient Lifelong Model Evaluation in an Era of Rapid Progress.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Universal In-Context Approximation By Prompting Fully Recurrent Models.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Label Delay in Online Continual Learning.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2024, 2024
Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Prompting a Pretrained Transformer Can Be a Universal Approximator.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Efficient Error Certification for Physics-Informed Neural Networks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Illusory Attacks: Information-theoretic detectability matters in adversarial attacks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
On Pretraining Data Diversity for Self-Supervised Learning.
Proceedings of the Computer Vision - ECCV 2024, 2024
SimCS: Simulation for Domain Incremental Online Continual Segmentation.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
2023
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective.
IEEE Trans. Pattern Anal. Mach. Intell., April, 2023
Catastrophic overfitting can be induced with discriminative non-robust features.
Trans. Mach. Learn. Res., 2023
Label Delay in Continual Learning.
CoRR, 2023
From Categories to Classifier: Name-Only Continual Learning by Exploring the Web.
CoRR, 2023
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation.
CoRR, 2023
Provably Correct Physics-Informed Neural Networks.
CoRR, 2023
Real-Time Evaluation in Online Continual Learning: A New Paradigm.
CoRR, 2023
Constrained Clustering: General Pairwise and Cardinality Constraints.
IEEE Access, 2023
RANCER: Non-Axis Aligned Anisotropic Certification with Randomized Smoothing.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
Language Model Tokenizers Introduce Unfairness Between Languages.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Certifying Ensembles: A General Certification Theory with S-Lipschitzness.
Proceedings of the International Conference on Machine Learning, 2023
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Computationally Budgeted Continual Learning: What Does Matter?
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Real-Time Evaluation in Online Continual Learning: A New Hope.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
2022
ANCER: Anisotropic Certification via Sample-wise Volume Maximization.
Trans. Mach. Learn. Res., 2022
SimCS: Simulation for Online Domain-Incremental Continual Segmentation.
CoRR, 2022
Illusionary Attacks on Sequential Decision Makers and Countermeasures.
CoRR, 2022
Catastrophic overfitting is a bug but also a feature.
CoRR, 2022
Data dependent randomized smoothing.
Proceedings of the Uncertainty in Artificial Intelligence, 2022
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Diversified Dynamic Routing for Vision Tasks.
Proceedings of the Computer Vision - ECCV 2022 Workshops, 2022
Combating Adversaries with Anti-adversaries.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
DeformRS: Certifying Input Deformations with Randomized Smoothing.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
2021
Rethinking Clustering for Robustness.
Proceedings of the 32nd British Machine Vision Conference 2021, 2021
2020
Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives.
PhD thesis, 2020
Network Moments: Extensions and Sparse-Smooth Attacks.
CoRR, 2020
ClusTR: Clustering Training for Robustness.
CoRR, 2020
On the Decision Boundaries of Deep Neural Networks: A Tropical Geometry Perspective.
CoRR, 2020
A Stochastic Derivative Free Optimization Method with Momentum.
Proceedings of the 8th International Conference on Learning Representations, 2020
Gabor Layers Enhance Network Robustness.
Proceedings of the Computer Vision - ECCV 2020, 2020
A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
2019
Constrained K-means with General Pairwise and Cardinality Constraints.
CoRR, 2019
Probabilistically True and Tight Bounds for Robust Deep Neural Network Training.
CoRR, 2019
Analytical Moment Regularizer for Gaussian Robust Networks.
CoRR, 2019
Local Color Mapping Combined with Color Transfer for Underwater Image Enhancement.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2019
Deep Layers as Stochastic Solvers.
Proceedings of the 7th International Conference on Learning Representations, 2019
2018
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild.
Proceedings of the Computer Vision - ECCV 2018, 2018
Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian Input.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018
2017
High Order Tensor Formulation for Convolutional Sparse Coding.
Proceedings of the IEEE International Conference on Computer Vision, 2017
FFTLasso: Large-Scale LASSO in the Fourier Domain.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
2016
Target Response Adaptation for Correlation Filter Tracking.
Proceedings of the Computer Vision - ECCV 2016, 2016
In Defense of Sparse Tracking: Circulant Sparse Tracker.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
3D Part-Based Sparse Tracker with Automatic Synchronization and Registration.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
2015
Multi-template Scale-Adaptive Kernelized Correlation Filters.
Proceedings of the 2015 IEEE International Conference on Computer Vision Workshop, 2015