相关论文: SALMUBench: A Benchmark for Sensitive Association-…

Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information. Existing unlearning methods typically formulate forgetting and retention as a regularized…

The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…

Human perception of similarity across uni- and multimodal inputs is highly complex, making it challenging to develop automated metrics that accurately mimic it. General purpose vision-language models, such as CLIP and large multi-modal…

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained model while preserving its knowledge of the remaining "retain" data. Existing MU methods based on label manipulation or model weight perturbations…

This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowledge distillation (KD) technique to tackle the problem, they…

With the increasing demand for the right to be forgotten, machine unlearning (MU) has emerged as a vital tool for enhancing trust and regulatory compliance by enabling the removal of sensitive data influences from machine learning (ML)…

Semi-supervised learning has become increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation…

Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully remove sensitive or harmful knowledge, this ``forgotten" information remains precariously…

Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primarily on data-centric or weight-based strategies frequently…

Unlearning in large language models (LLMs) involves precisely removing specific information from a pre-trained model. This is crucial to ensure safety of LLMs by deleting private data or harmful knowledge acquired during pre-training.…

A common assumption in multimodal learning is the completeness of training data, i.e., full modalities are available in all training examples. Although there exists research endeavor in developing novel methods to tackle the incompleteness…

Malignant brain tumors have become an aggressive and dangerous disease that leads to death worldwide.Multi-modal MRI data is crucial for accurate brain tumor segmentation, but missing modalities common in clinical practice can severely…

Inter-scanner variability of magnetic resonance imaging has an adverse impact on the diagnostic and prognostic quality of the scans and necessitates the development of models robust to domain shift inflicted by the unseen scanner data.…

Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning methods have shown promise, they still struggle with the…

Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers…

Pretrained Multimodal Large Language Models (MLLMs) are increasingly used in sensitive domains such as medical AI, where privacy regulations like HIPAA and GDPR require specific removal of individuals' or institutions' data. This motivates…

Learning from multiple modalities often suffers from imbalance, where information-rich modalities dominate optimization while weaker or partially missing modalities contribute less. This imbalance becomes severe in realistic settings with…

Spatial cognition is fundamental to real-world multimodal intelligence, allowing models to effectively interact with the physical environment. While multimodal large language models (MLLMs) have made significant strides, existing benchmarks…