Laplace Learning in Wasserstein Space

The paper presents a self-training framework for detecting offensive content on social media, addressing the challenge of limited labeled data. It utilizes Multi-Agent Vision-Language Models (MA-VLMs) to collaboratively assign pseudo-labels to unlabeled data. The framework distinguishes between Agreed-Unknown and Disagreed-Unknown sets based on classifier and MA-VLM agreement. By simulating dual perspectives, it enhances label reliability and employs a Positive-Negative-Unlabeled (PNU) loss for optimization, aiming to improve detection accuracy in low-resource settings.

The paper discusses the challenges of test-time prompt tuning for vision-language models, highlighting the issue of prompt optimization bias that can lead to suboptimal performance in downstream tasks. It identifies two main causes: the model's focus on entropy minimization, which may overlook prediction accuracy, and data misalignment between visual and textual modalities. To address these issues, the authors propose a new method called Doubly Debiased Test-Time Prompt Tuning, aimed at improving model performance in zero-shot settings.

The article presents a novel approach to volumetric medical image segmentation called Coordinative Ordinal-Relational Anatomical Learning (CORAL). This method addresses challenges in segmenting medical images by utilizing continuous anatomical similarity instead of relying on hard binary thresholds. CORAL aims to improve the accuracy of segmentation by capturing both local and global anatomical structures, thereby enhancing the understanding of anatomical progression across different patients.

The article presents FlowPath, a novel method for modeling continuous-time dynamics from sparse and irregularly-sampled time series. It addresses the limitations of existing methods that rely on fixed interpolation schemes, which can misrepresent data. FlowPath utilizes an invertible neural flow to create a continuous, data-adaptive manifold, enhancing classification accuracy significantly across 18 benchmark datasets.