About
Research & Development
Optimizing Transformer Efficiency for 6G Edge Devices Through Adaptive Token Merging
TLDR: A new training-free framework called Adaptive Pareto-Optimal Token Merging has been developed to make large transformer models more efficient for edge devices in...
Research & Development
Enhancing Speech Recognition for Rare Words with a New Keyword-Focused Training Method
TLDR: This research introduces a novel keyword-aware loss function to improve the training of contextual biasing modules in Automatic Speech Recognition (ASR) systems, especially...
Research & Development
Vejde: Enabling Adaptive AI for Relational Data Challenges
TLDR: Vejde is a new framework that combines graph neural networks and reinforcement learning to create AI policies that can learn to make decisions...
Research & Development
Virtual Staining Unlocks 3D Insights into Bone Implants from X-ray Scans
TLDR: Researchers developed a deep learning model that can "virtually stain" 3D X-ray scans of bone implants, transforming greyscale X-ray images into colorized histology-like...
Research & Development
MatCha: A New Benchmark for Multimodal AI in Materials Characterization
TLDR: The paper introduces MatCha, the first benchmark for evaluating multimodal large language models (MLLMs) on materials characterization image understanding. Comprising 1,500 expert-level questions...
Research & Development
Polynomial Regression: A Robust Approach to Non-Linear Correlation Measurement
TLDR: Researchers Luca Giuliani and Michele Lombardi have developed a new method, HGR-KB, for calculating the Hirschfeld–Gebelein–Rényi (HGR) correlation coefficient, which captures complex non-linear...