Related papers: SALMUBench: A Benchmark for Sensitive Association-…

Machine learning models play a vital role in making predictions and deriving insights from data and are being increasingly used for causal inference. To preserve user privacy, it is important to enable the model to forget some of its…

Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal sensitive information, raising ethical and privacy concerns.…

Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, we…

As text-to-image diffusion models gain widespread commercial applications, there are increasing concerns about unethical or harmful use, including the unauthorized generation of copyrighted or sensitive content. Concept unlearning has…

The trustworthy machine learning (ML) community is increasingly recognizing the crucial need for models capable of selectively 'unlearning' data points after training. This leads to the problem of machine unlearning (MU), aiming to…

Multimodal physiological data powers clinical AI systems from intensive care units to wearable devices, but sensors routinely fail in practice. Two failure modes are common: modality missing, where an entire channel is absent, and…

Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine…

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…

Multi-annotator learning (MAL) aims to model annotator-specific labeling patterns. However, existing methods face a critical challenge: they simply skip updating annotator-specific model parameters when encountering missing labels, i.e., a…

Foundation models (FMs) such as CLIP have demonstrated impressive zero-shot performance across various tasks by leveraging large-scale, unsupervised pre-training. However, they often inherit harmful or unwanted knowledge from noisy…

Multimodal learning has gained attention for its capacity to integrate information from different modalities. However, it is often hindered by the multimodal imbalance problem, where certain modality dominates while others remain…

We propose new methodologies for both unlearning random set of samples and class unlearning and show that they outperform existing methods. The main driver of our unlearning methods is the similarity of predictions to a retrained model on…

Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from…

Machine unlearning methods aim to remove sensitive or unwanted content from trained models, but typically demand extensive model updates at significant computational cost while potentially degrading model performance on both related and…

Machine unlearning offers effective solutions for revoking the influence of specific training data on pre-trained model parameters. While existing approaches address unlearning for classification and generative models, they overlook an…

Machine unlearning is a crucial tool for enabling a classification model to forget specific data that are used in the training time. Recently, various studies have presented machine unlearning algorithms and evaluated their methods on…

Large Multimodal Models (LMMs) exhibit major shortfalls when interpreting images and, by some measures, have poorer spatial cognition than small children or animals. Despite this, they attain high scores on many popular visual benchmarks,…

Privacy concerns associated with machine learning models have driven research into machine unlearning, which aims to erase the memory of specific target training data from already trained models. This issue also arises in federated…

Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that…

The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…