Mohsen Hooshmand

works on

contrastive learning 1 denoising autoencoder 1 perturbation robustness 1 pretrained language models 1 sentence embeddings 1

From the 1 of 3 linked papers with an AI index.

collaborators

Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising

Sina Heydari, Amirreza Abbasi, Mohsen Hooshmand +1

The paper introduces a lightweight Contrastive Denoising Autoencoder (CDAE) that refines BERT sentence embeddings to be more robust against semantic-preserving perturbations by joi…