About
Research & Development
Subgroup-Targeted Poisoning: A New Stealth Attack on Federated Recommender Systems
TLDR: This research introduces Spattack, a novel and stealthy poisoning attack designed for Federated Recommender Systems (FedRec). Unlike previous attacks that target all users,...
Research & Development
SPATIA: A New AI Model for Understanding Cells in Their Natural Environment
TLDR: SPATIA is a novel AI model that integrates cellular morphology, gene expression, and spatial organization across multiple scales (cell, niche, tissue) to understand...
Research & Development
A New Approach to X-ray Image Learning: Polyrepresentation
TLDR: A novel 'polyrepresentation' approach combines multiple data representations (Siamese Network embeddings, self-supervised features, radiomic features) for X-ray images, demonstrating improved performance, transferability to...
Research & Development
Advancing Robot Motion Planning Through Merging Diverse Datasets
TLDR: Interaction-Merged Motion Planning (IMMP) is a new method that improves autonomous robot motion planning by effectively leveraging diverse motion datasets. It addresses challenges...
Research & Development
Streamlining Neural Networks: Progressive Channel Pruning for Efficient AI Deployment
TLDR: Progressive Channel Pruning (PCP) is a novel iterative framework for compressing Convolutional Neural Networks (CNNs). It employs a three-step pipeline—attempting, selecting, and pruning—to...
Research & Development
Understanding How Computers Generate Puns: A Comprehensive Review
TLDR: This paper provides the first comprehensive survey on pun generation, systematically reviewing datasets, conventional methods, deep learning techniques, and pre-trained language models. It...