About
Research & Development
Advancing Video Compression with AI: A New Era of Perceptually Optimized Content
TLDR: A new video compression framework uses conditional diffusion models to generate high-quality video from sparse information, focusing on human perceptual quality rather than...
Research & Development
Advancing Time-Series Analysis: New Methods for Optimal Filtering and Smoothing with Preferential Subspace Identification
TLDR: This research extends Preferential Subspace Identification (PSID), a method for modeling two time-series (e.g., neural activity and behavior), to enable optimal filtering and...
Research & Development
AI Model Enhances Lung CT Scans for Better Diagnosis and Prognosis
TLDR: A new AI model, TVSRN-V2, utilizes transformer technology to convert low-resolution lung CT scans into high-resolution images. This innovation significantly improves the accuracy...
Research & Development
Unpacking LLMs’ Metaphor Skills: Surface Features Over Deep Understanding
TLDR: A research paper evaluates Large Language Models (LLMs) on metaphor interpretation, finding that their performance is primarily driven by surface features like lexical...
Research & Development
SynDiff: Enhancing Medical Image Segmentation with Text-Guided Synthetic Data and Single-Step Diffusion
TLDR: SynDiff is a new framework that uses text-guided synthetic data generation to augment limited medical datasets and a single-step diffusion model for efficient,...
Research & Development
Smart Surfaces for Multi-Beam Wireless: Optimizing Signal Delivery and Controlling Reradiation
TLDR: This research investigates the joint design of transmit precoding and Reconfigurable Intelligent Surface (RIS) phase shifts in multi-user MIMO systems. It aims to...