Related papers: Increasing Information Extraction in Low-Signal Re…

Large language models (LLMs) have shown promising capabilities in visually interpreting medical time-series data. However, their general-purpose design can limit domain-specific precision, and the proprietary nature of many models poses…

Few-shot relation classification seeks to classify incoming query instances after meeting only few support instances. This ability is gained by training with large amount of in-domain annotated data. In this paper, we tackle an even harder…

Pathological image analysis is an important process for detecting abnormalities such as cancer from cell images. However, since the image size is generally very large, the cost of providing detailed annotations is high, which makes it…

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be…

A major bottleneck in imitation learning is the requirement of a large number of expert demonstrations, which can be expensive or inaccessible. Learning from supplementary demonstrations without strict quality requirements has emerged as a…

In-context Learning (ICL) is the ability of Large Language Models (LLMs) to perform new tasks when conditioned on prompts comprising a few task examples. However, ICL performance can be critically sensitive to the choice of examples. To…

The efficacy of mathematical models heavily depends on the quality of the training data, yet collecting sufficient data is often expensive and challenging. Many modeling applications require inferring parameters only as a means to predict…

Modern foundation models provide highly expressive visual representations, yet adapting them to high-resolution medical imaging remains challenging due to limited annotations and weak supervision. Mammography, in particular, is…

In many real-world tasks, particularly those involving data objects with complicated semantics such as images and texts, one object can be represented by multiple instances and simultaneously be associated with multiple labels. Such tasks…

Learning from temporally-correlated data is a core facet of modern machine learning. Yet our understanding of sequential learning remains incomplete, particularly in the multi-trajectory setting where data consists of many independent…

Multiple instance learning (MIL) is a powerful approach to classify whole slide images (WSIs) for diagnostic pathology. A fundamental challenge of MIL on WSI classification is to discover the \textit{critical instances} that trigger the bag…

Multi-label learning (MLL) learns from the examples each associated with multiple labels simultaneously, where the high cost of annotating all relevant labels for each training example is challenging for real-world applications. To cope…

We address the problem of \emph{instance label stability} in multiple instance learning (MIL) classifiers. These classifiers are trained only on globally annotated images (bags), but often can provide fine-grained annotations for image…

A multi-modal machine learning system uses multiple unique data sources and types to improve its performance. This article proposes a system that combines results from several types of models, all of which are trained on different data…

Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \textit{imprecise} labels, is a commonplace challenge in machine learning tasks. Previous methods…

Large Language Models (LLMs) have showcased their In-Context Learning (ICL) capabilities, enabling few-shot learning without the need for gradient updates. Despite its advantages, the effectiveness of ICL heavily depends on the choice of…

Multi-Instance Learning (MIL) has shown impressive performance for histopathology whole slide image (WSI) analysis using bags or pseudo-bags. It involves instance sampling, feature representation, and decision-making. However, existing…

Multiple Instance Learning (MIL) has been widely applied to medical imaging diagnosis, where bag labels are known and instance labels inside bags are unknown. Traditional MIL assumes that instances in each bag are independent samples from a…

Large Multimodal Models (LMMs) have made significant breakthroughs with the advancement of instruction tuning. However, while existing models can understand images and videos at a holistic level, they still struggle with instance-level…

Information theoretic sensor management approaches are an ideal solution to state estimation problems when considering the optimal control of multi-agent systems, however they are too computationally intensive for large state spaces,…