Foundation models have emerged as a powerful tool for many AI problems. Despite the
tremendous success of foundation models, effective adaptation to new tasks, particularly …

Training data privacy is a fundamental problem in modern Artificial Intelligence (AI)
applications, such as face recognition, recommendation systems, language generation, and …

Visual category discovery methods aim to find novel categories in unlabeled visual data. At
training time, a set of labeled and unlabeled images are provided, where the labels …

The softmax activation function plays a crucial role in the success of large language models
(LLMs), particularly in the self-attention mechanism of the widely adopted Transformer …

Generalized Category Discovery (GCD) aims to classify unlabelled images from
bothseen'andunseen'classes by transferring knowledge from a set of labelledseen'class …

The application of transformer-based models on time series forecasting (TSF) tasks has long
been popular to study. However, many of these works fail to beat the simple linear residual …

In recent years, synthetic aperture radar automatic target recognition (SAR ATR) has been
widely researched for its ability to achieve high-performance target classification through …

The computational intensity of Large Language Models (LLMs) is a critical bottleneck,
primarily due to the $ O (n^ 2) $ complexity of the attention mechanism in transformer …

Identifying anomalous trajectories that deviate from usual driving patterns in an open-world
context has recently become a critical and urgent task in location-aware systems. In contrast …

Semi-supervised domain adaptation (SSDA) aims to adapt a model trained on an annotated
source domain to a related, but different, target domain with limited labeled and abundant …