Web-crawled pretraining datasets underlie the impressive" zero-shot" evaluation
performance of multimodal models, such as CLIP for classification and Stable-Diffusion for …

Continual learning (CL) aims to help deep neural networks learn new knowledge while
retaining what has been learned. Owing to their powerful generalizability, pre-trained vision …

Multimodal foundation models serve numerous applications at the intersection of vision and
language. Still, despite being pretrained on extensive data, they become outdated over time …

Requiring extensive human supervision is often impractical for continual learning due to its
cost, leading to the emergence of'name-only continual learning'that only provides the name …

Continual segmentation has not yet tackled the challenge of improving open-vocabulary
segmentation models with training data for accurate segmentation across large, continually …

Model merging combines multiple expert models-finetuned from a base foundation model
on diverse tasks and domains-into a single, more capable model. However, most existing …

Class imbalance and label noise are pervasive in large-scale datasets, yet much of machine
learning research assumes well-labeled, balanced data, which rarely reflects real world …