Related papers: Removing Biases from Molecular Representations via…

In this paper, we study the cross-modal image retrieval, where the inputs contain a source image plus some text that describes certain modifications to this image and the desired image. Prior work usually uses a three-stage strategy to…

Identifying relationships between molecular variations and their clinical presentations has been challenged by the heterogeneous causes of a disease. It is imperative to unveil the relationship between the high dimensional molecular…

High-throughput screening, in which multiwell plates are used to test large numbers of compounds against specific targets, is widely used across many areas of the biological sciences and most prominently in drug discovery. We propose a…

Recommender systems suffer from confounding biases when there exist confounders affecting both item features and user feedback (e.g., like or not). Existing causal recommendation methods typically assume confounders are fully observed and…

We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a prevalent source of information online, it is essential for RAG systems to integrate information…

Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, where predictions rely disproportionately on a single modality. Prior approaches primarily…

Link prediction (LP) is a fundamental task in graph representation learning, with numerous applications in diverse domains. However, the generalizability of LP models is often compromised due to the presence of noisy or spurious information…

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their…

The use of multimodal data in assisted diagnosis and segmentation has emerged as a prominent area of interest in current research. However, one of the primary challenges is how to effectively fuse multimodal features. Most of the current…

In the drug discovery process, the low success rate of drug candidate screening often leads to insufficient labeled data, causing the few-shot learning problem in molecular property prediction. Existing methods for few-shot molecular…

A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective…

Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept-layer topological alignment, under which…

Deep InfoMax (DIM) is a well-established method for self-supervised representation learning (SSRL) based on maximization of the mutual information between the input and the output of a deep neural network encoder. Despite the DIM and…

Semi-supervised image classification, leveraging pseudo supervision and consistency regularization, has demonstrated remarkable success. However, the ongoing challenge lies in fully exploiting the potential of unlabeled data. To address…

Contrastive learning has emerged as a cornerstone of unsupervised representation learning across vision, language, and graph domains, with InfoNCE as its dominant objective. Despite its empirical success, the theoretical underpinnings of…

Unsupervised deformable image registration requires aligning complex anatomical structures without reference labels, making interpretability and reliability critical. Existing deep learning methods achieve considerable accuracy but often…

Motivation: As cancer researchers have come to appreciate the importance of intratumor heterogeneity, much attention has focused on the challenges of accurately profiling heterogeneity in individual patients. Experimental technologies for…

Text representations learned by machine learning models often encode undesirable demographic information of the user. Predictive models based on these representations can rely on such information, resulting in biased decisions. We present a…

This paper introduces MovieCORE, a novel video question answering (VQA) dataset designed to probe deeper cognitive understanding of movie content. Unlike existing datasets that focus on surface-level comprehension, MovieCORE emphasizes…

Information Extraction from visually rich documents is a challenging task that has gained a lot of attention in recent years due to its importance in several document-control based applications and its widespread commercial value. The…