Publications
2023
CoTFormer: More Tokens With Attention Make Up For Less Depth Miscellaneous
2023.
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models Miscellaneous
2023.
Collaborative Learning via Prediction Consensus Miscellaneous
2023.
DRCFS: Doubly Robust Causal Feature Selection Miscellaneous
2023.
DocILE Benchmark for Document Information Localization and Extraction Proceedings Article
In: Fink, Gernot A.; Jain, Rajiv; Kise, Koichi; Zanibbi, Richard (Ed.): Document Analysis and Recognition – ICDAR 2023, pp. 147–166, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-41679-8.
Efficient Certified Training and Robustness Verification of Neural ODEs Miscellaneous
2023.
Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems Miscellaneous
2023.
Fair Empirical Risk Minimization Revised Proceedings Article
In: Rojas, Ignacio; Joya, Gonzalo; Catala, Andreu (Ed.): Advances in Computational Intelligence, pp. 29–42, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-43085-5.
Fast Feature Selection with Fairness Constraints Miscellaneous
2023.
Faster Causal Attention Over Large Sequences Through Sparse Flash Attention Miscellaneous
2023.
FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines Miscellaneous
2023.
Fuzzy Detectors Against Adversarial Attacks Proceedings Article
In: 2023.
Generating Scenarios from High-Level Specifications for Object Rearrangement Tasks Proceedings Article
In: pp. 11420-11427, 2023.
Human Uncertainty in Concept-Based AI Systems Proceedings Article
In: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, pp. 869–889, Association for Computing Machinery, , Montréal, QC, Canada,, 2023, ISBN: 9798400702310.
Human-in-the-Loop Mixup Proceedings Article
In: The 39th Conference on Uncertainty in Artificial Intelligence, 2023.
Individual Privacy Accounting with Gaussian Differential Privacy Miscellaneous
2023.
Interpretable-through-prototypes deepfake detection for diffusion models Proceedings Article
In: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 467-474, 2023.
Irreducible Curriculum for Language Model Pretraining Miscellaneous
2023.
LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games Miscellaneous
2023.
Landmark Attention: Random-Access Infinite Context Length for Transformers Miscellaneous
2023.
Large Class Separation is Not What You Need for Relational Reasoning-Based OOD Detection Proceedings Article
In: Foresti, Gian Luca; Fusiello, Andrea; Hancock, Edwin (Ed.): Image Analysis and Processing – ICIAP 2023, pp. 295–306, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-43153-1.
Learning Counterfactually Invariant Predictors Miscellaneous
2023.
Let’s ViCE! Mimicking Human Cognitive Behavior in Image Generation Evaluation Miscellaneous
2023.
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models Miscellaneous
2023.
Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models Miscellaneous
2023.
MargCTGAN: A “Marginally” Better CTGAN for the Low Sample Regime Journal Article
In: 2023.
Multi-task Representation Learning with Stochastic Linear Bandits Miscellaneous
2023.
Multiplication-Free Transformer Training via Piecewise Affine Operations Miscellaneous
2023.
Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning Miscellaneous
2023.
Noise-Aware Statistical Inference with Differentially Private Synthetic Data Miscellaneous
2023.
Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection Miscellaneous
2023.
On Adversarial Training without Perturbing all Examples Miscellaneous
2023.
On the Efficacy of Differentially Private Few-shot Image Classification Miscellaneous
2023.
On the Informativeness of Supervision Signals Proceedings Article
In: The 39th Conference on Uncertainty in Artificial Intelligence, 2023.
Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images Miscellaneous
2023.
Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation Miscellaneous
2023.
Private and Collaborative Kaplan-Meier Estimators Miscellaneous
2023.
PØDA: Prompt-driven Zero-shot Domain Adaptation Miscellaneous
2023.
Robust Meta-Representation Learning via Global Label Inference and Classification Miscellaneous
2023.
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models Miscellaneous
2023.
SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models Miscellaneous
2023.
SynthCap: Augmenting Transformers with Synthetic Data for Image Captioning Proceedings Article
In: Foresti, Gian Luca; Fusiello, Andrea; Hancock, Edwin (Ed.): Image Analysis and Processing – ICIAP 2023, pp. 112–123, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-43148-7.
TAPS: Connecting Certified and Adversarial Training Miscellaneous
2023.
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoder for Text Recognition and Document Enhancement Journal Article
In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 2, pp. 2330-2338, 2023.
Towards Randomized Algorithms and Models that We Can Trust: a Theoretical Perspective Proceedings Article
In: Ciaco – i6doc.com, 2023.
Towards interpretable-by-design deep learning algorithms Miscellaneous
2023.
Trading-off payments and accuracy in online classification with paid stochastic experts Proceedings Article
In: JMLR.org, , Honolulu, Hawaii, USA,, 2023.
Unmasking Anomalies in Road-Scene Segmentation Miscellaneous
2023.
Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis Proceedings Article
In: Foresti, Gian Luca; Fusiello, Andrea; Hancock, Edwin (Ed.): Image Analysis and Processing – ICIAP 2023, pp. 345–356, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-43153-1.