Optimizing RNA design with AI and an Ising machine: Encoding matters

RNA has emerged as one of the most promising molecules in modern medicine, enabling advances from mRNA vaccines and gene ...
IEEE

An Intriguing Struggle of CNNs in JPEG Steganalysis and the OneHot Solution

Abstract: Deep convolutional neural networks (CNNs) have become the tool of choice for steganalysis because they outperform older feature-based detectors by a large margin. However, recent work points ...
Hacker

What is One Hot Encoding? Why And When do you have to use it?

So, you’re playing with ML models and you encounter this “One hot encoding” term all over the place. You see the sklearn documentation for one hot encoder and it says “ Encode categorical integer ...
GitHub

Efficient LLM-Serving with Proxy Models

This repository contains the code for the paper "Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction" (link). The key idea/observation is that a small proxy model (i.e.
sei.cmu

Explainability in Cybersecurity Data Science

Mellon, J., and Worrell, C., 2023: Explainability in Cybersecurity Data Science. Software Engineering Institute blog, Accessed July 8, 2026, https://doi.org/10.58012 ...
IEEE

Performance Comparison of Typical Binary-Integer Encodings in an Ising Machine

Abstract: The differences in performance among binary-integer encodings in an Ising machine, which can solve combinatorial optimization problems, are investigated. Many combinatorial optimization ...