You can also find my articles on my Google Scholar profile.

Variational prompt tuning improves generalization of vision-language models

Published in Arxiv, 2022

In this paper, we propose a probabilistic modeling of the underlying distribution of prompts, allowing prompts within the support of an associated concept to be derived through stochastic sampling. This results in a more complete and richer transfer of the information captured by the language model, providing better generalization capabilities for downstream tasks. Read more

LifeLonger: A Benchmark for Continual Disease Classification

Published in International Conference on Medical Image Computing and Computer Assisted Intervention, 2022

In this paper we introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection, by applying existing state-of-the-art continual learning methods. Read more

Generative Kernel Continual Learning

Published in Arxiv, 2021

In this paper, we introduce generative kernel continual learning, which explores and exploits the synergies between generative models and kernels for continual learning. Read more

Kernel Continual Learning

Published in International Conference of Machine Leanring (ICML), 2021

This paper introduces kernel continual learning, a simple but effective variant of continual learning that leverages the non-parametric nature of kernel methods to tackle catastrophic forgetting. Read more