Related papers: Zero-Shot Class Unlearning in CLIP with Synthetic …

Document understanding models have recently demonstrated remarkable performance by leveraging extensive collections of user documents. However, since documents often contain large amounts of personal data, their usage can pose a threat to…

Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this reliance poses privacy risks, as hackers may…

In the era of foundation models, CLIP has emerged as a powerful tool for aligning text & visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visual features for…

We propose DiffCLIP, a novel vision-language model that extends the differential attention mechanism to CLIP architectures. Differential attention was originally developed for large language models to amplify relevant context while…

Training machine learning models requires the storage of large datasets, which often contain sensitive or private data. Storing data is associated with a number of potential risks which increase over time, such as database breaches and…

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten."…

Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such models require a massive amount of pre-training data. Improving…

Algorithm selection is commonly used to predict the best solver from a portfolio per per-instance. In many real scenarios, instances arrive in a stream: new instances become available over time, while the number of class labels can also…

Vision-language pre-training such as CLIP enables zero-shot transfer that can classify images according to the candidate class names. While CLIP demonstrates an impressive zero-shot performance on diverse downstream tasks, the distribution…

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit…

Machine unlearning aims to remove knowledge of the specific training data in a well-trained model. Currently, machine unlearning methods typically handle all forgetting data in a single batch, removing the corresponding knowledge all at…

Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the…

Machine unlearning strives to uphold the data owners' right to be forgotten by enabling models to selectively forget specific data. Recent advances suggest pre-computing and storing statistics extracted from second-order information and…

Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data. However, adapting pre-trained VLMs to a sequence of downstream tasks often leads to the forgetting of previously…

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model, i.e., CLIP has…

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy…

Class-Incremental Unsupervised Domain Adaptation (CI-UDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where the sets of potential target classes appearing at different time steps are disjoint and are…

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…

Large-scale vision-language pre-trained (VLP) models (e.g., CLIP) are renowned for their versatility, as they can be applied to diverse applications in a zero-shot setup. However, when these models are used in specific domains, their…