4 papers
TabQL: In-Context Q-Learning with Tabular Foundation Models
Qisai Liu, Zhanhong Jiang, Timilehin Ayanlade +4
We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation mod…
Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing
A K Nirala, A Joshi, C Hegde +1
A key benefit of deep vision-language models such as CLIP is that they enable zero-shot open vocabulary classification; the user has the ability to define novel class labels via na…
Vulnerability-Aware Instance Reweighting For Adversarial Training
Olukorede Fakorede, Ashutosh Kumar Nirala, Modeste Atsague +1
Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by inclu…
Improving Adversarial Robustness with Hypersphere Embedding and Angular-based Regularizations
Olukorede Fakorede, Ashutosh Nirala, Modeste Atsague +1
Adversarial training (AT) methods have been found to be effective against adversarial attacks on deep neural networks. Many variants of AT have been proposed to improve its perform…