Related papers: PI-NAIM: Path-Integrated Neural Adaptive Imputatio…

The increasing prevalence and growing size of data in modern applications have led to high costs for computation in traditional processor-centric computing systems. Moving large volumes of data between memory devices (e.g., DRAM) and…

Missing modalities are a common challenge in real-world multimodal learning scenarios, occurring during both training and testing. Existing methods for managing missing modalities often require the design of separate prompts for each…

Neural Posterior Estimation (NPE) enables rapid parameter inference for complex simulators with intractable likelihoods. NPE trains an inference network to estimate a probability density over parameters given data, typically assumed to be…

Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of…

Quantifying and propagating modeling uncertainties is crucial for reliability analysis, robust optimization, and other model-based algorithmic processes in engineering design and control. Now, physics-informed machine learning (PIML)…

To maximize hardware efficiency and performance accuracy in Compute-In-Memory (CIM)-based neural network accelerators for Artificial Intelligence (AI) applications, co-optimizing both software and hardware design parameters is essential.…

Incomplete multi-modal medical image segmentation faces critical challenges from modality imbalance, including imbalanced modality missing rates and heterogeneous modality contributions. Due to their reliance on idealized assumptions of…

Visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same pedestrian from different modalities, where the challenges lie in the significant modality discrepancy. To alleviate the modality gap, recent methods…

Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…

We propose a unified deep meta-learning framework for accelerated magnetic resonance imaging (MRI) that jointly addresses multi-coil reconstruction and cross-modality synthesis. Motivated by the limitations of conventional methods in…

Multimodal neuroimaging provides complementary insights for Alzheimer's disease diagnosis, yet clinical datasets frequently suffer from missing modalities. We propose ACADiff, a framework that synthesizes missing brain imaging modalities…

This paper introduces the Bidirectional Clustered MPPI (BiC-MPPI) algorithm, a novel trajectory optimization method aimed at enhancing goal-directed guidance within the Model Predictive Path Integral (MPPI) framework. BiC-MPPI incorporates…

State-of-the-art causal discovery methods usually assume that the observational data is complete. However, the missing data problem is pervasive in many practical scenarios such as clinical trials, economics, and biology. One…

Multimodal learning has shown promise in medical imaging, combining complementary modalities like images and text. Vision-language models (VLMs) capture rich diagnostic cues but often require large paired datasets and prompt- or text-based…

In Masked Image Modeling (MIM), two primary methods exist: Pixel MIM and Latent MIM, each utilizing different reconstruction targets, raw pixels and latent representations, respectively. Pixel MIM tends to capture low-level visual details…

Masked Image Modeling (MIM) has become an essential method for building foundational visual models in remote sensing (RS). However, the limitations in size and diversity of existing RS datasets restrict the ability of MIM methods to learn…

It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features. In this work, we propose "Amending Inherent Interpretability via Self-Supervised Masking" (AIM), a simple yet interestingly effective…

Advances in AI have introduced several strong models in computational pathology to usher it into the era of multi-modal diagnosis, analysis, and interpretation. However, the current pathology-specific visual language models still lack…

The integration of Artificial Intelligence (AI) in medical diagnostics is often hindered by model opacity, where high-accuracy systems function as "black boxes" without transparent reasoning. This limitation is critical in clinical…

Multimodal federated learning enables privacy-preserving collaborative model training across healthcare institutions. However, a fundamental challenge arises from modality heterogeneity: many clinical sites possess only a subset of…