The recent success of large language models (LLMs) trained on static, pre-collected,
general datasets has sparked numerous research directions and applications. One such …

Contrastive pre-training of image-text foundation models such as CLIP demonstrated
excellent zero-shot performance and improved robustness on a wide range of downstream …

Continual learning has gained substantial attention within the deep learning community
offering promising solutions to the challenging problem of sequential learning. Yet a largely …

Due to the rapid generation and dissemination of information, large language models
(LLMs) quickly run out of date despite enormous development costs. Due to this crucial need …

Modern pre-trained architectures struggle to retain previous information while undergoing
continuous fine-tuning on new tasks. Despite notable progress in continual classification …

Continual learning is the problem of integrating new information in a model while retaining
the knowledge acquired in the past. Despite the tangible improvements achieved in recent …

We propose RanDumb to examine the efficacy of continual representation learning.
RanDumb embeds raw pixels using a fixed random transform which approximates an RBF …

Language models (LMs) are known to suffer from forgetting of previously learned examples
when fine-tuned, breaking stability of deployed LM systems. Despite efforts on mitigating …

Deep learning, despite its broad applicability, grapples with robustness challenges in real-
world applications, especially when training and test distributions differ. Reasons for the …