Staffing & Scheduling

WeakSupCon: Weakly Supervised Contrastive Learning for Encoder Pre-training

Weakly supervised multiple instance learning (MIL) is a challenging task given that only bag-level labels are provided, while each bag typically contains multiple instances. This topic has been extensively studied in histopathological image analysis, where labels are usually available only at the whole slide image (WSI) level, while each whole slide image can be divided into thousands of small i...

JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba

Existing state-of-the-art feature matchers capture long-range dependencies with Transformers but are hindered by high spatial complexity, leading to demanding training and highlatency inference. Striking a better balance between performance and efficiency remains a challenge in feature matching. Inspired by the linear complexity O(N) of Mamba, we propose an ultra-lightweight Mamba-based matcher,...

Variance-Aware Loss Scheduling for Multimodal Alignment in Low-Data Settings

Training vision-language models for image-text alignment typically requires large datasets to achieve robust performance. In low-data scenarios, sta...

PathRWKV: Enabling Whole Slide Prediction with Recurrent-Transformer

Pathological diagnosis plays a critical role in clinical practice, where the whole slide images (WSIs) are widely applied. Through a two-stage parad...

A generalized approach to label shift: the Conditional Probability Shift Model

In many practical applications of machine learning, a discrepancy often arises between a source distribution from which labeled training examples ar...

An energy-efficient learning solution for the Agile Earth Observation Satellite Scheduling Problem

The Agile Earth Observation Satellite Scheduling Problem (AEOSSP) entails finding the subset of observation targets to be scheduled along the satell...

Dynamic Search for Inference-Time Alignment in Diffusion Models

Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remai...

The use of large language models to enhance cancer clinical trial educational materials.

BACKGROUND: Adequate patient awareness and understanding of cancer clinical trials is essential for trial recruitment, informed decision making, and p...

Systematic Literature Review on Clinical Trial Eligibility Matching

Clinical trial eligibility matching is a critical yet often labor-intensive and error-prone step in medical research, as it ensures that participant...

MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention

Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease. Mul...

FLStore: Efficient Federated Learning Storage for non-training workloads

Federated Learning (FL) is an approach for privacy-preserving Machine Learning (ML), enabling model training across multiple clients without central...

QFAL: Quantum Federated Adversarial Learning

Quantum federated learning (QFL) merges the privacy advantages of federated systems with the computational potential of quantum neural networks (QNN...

Generating patient cohorts from electronic health records using two-step retrieval-augmented text-to-SQL generation

Clinical cohort definition is crucial for patient recruitment and observational studies, yet translating inclusion/exclusion criteria into SQL queri...

Oscillation-Reduced MXFP4 Training for Vision Transformers

Pre-training Transformers in FP4 precision is becoming a promising approach to gain substantial speedup, but it comes with a considerable loss of ac...

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models

In recent years, Diffusion Models (DMs) have demonstrated significant advances in the field of image generation. However, according to current resea...

InstaFace: Identity-Preserving Facial Editing with Single Image Inference

Facial appearance editing is crucial for digital avatars, AR/VR, and personalized content creation, driving realistic user experiences. However, pre...

TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planning

Recent advancements in probing Large Language Models (LLMs) have explored their latent potential as personalized travel planning agents, yet existin...

Partial Orders for Precise and Efficient Dynamic Deadlock Prediction

Deadlocks are a major source of bugs in concurrent programs. They are hard to predict, because they may only occur under specific scheduling conditi...

Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning

Deep learning models lack shift invariance, making them sensitive to input shifts that cause changes in output. While recent techniques seek to addr...

Arbitrary Volumetric Refocusing of Dense and Sparse Light Fields

A four-dimensional light field (LF) captures both textural and geometrical information of a scene in contrast to a two-dimensional image that captur...