Security Boulevard

NDSS 2025 – PBP: Post-Training Backdoor Purification For Malware Classifiers

Dung Thuy Nguyen (Vanderbilt University), Ngoc N. Tran (Vanderbilt University), Taylor T. Johnson (Vanderbilt University), Kevin Leach (Vanderbilt University) PAPER PBP: Post-Training Backdoor ...
The Lancet

When to and when not to use machine learning in risk prediction models

Machine learning for health data science, fuelled by proliferation of data and reduced computational costs, has garnered considerable interest among researchers. The debate around the use of machine ...

MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

MIT researchers unveil a new fine-tuning method that lets enterprises consolidate their "model zoos" into a single, ...
The Lancet

From data to decision: the future of prehospital intubation in major trauma

The question of whether prehospital emergency anaesthesia and intubation improves survival in patients with major trauma has ...
Frontiers

Large Language Models for Knowledge-Intensive Domains: Methods, Systems, and Evaluation

The rapid emergence of Large Language Models (LLMs) and generative AI is reshaping how people and organizations access, synthesize, and apply knowledge.
IEEE

Predicting the dielectric properties of dielectric films in chip by machine learning methods

Abstract: With the continuous development of the semiconductor industry in terms of miniaturization and performance improvement, the drawbacks of traditional dielectric materials such as silicon ...
Communications of the ACM

Formal Reasoning Meets LLMs: Toward AI for Mathematics and Verification

Print Join the Discussion View in the ACM Digital Library The mathematical reasoning performed by LLMs is fundamentally different from the rule-based symbolic methods in traditional formal reasoning.
IEEE

Learning From Fish: A Two-Stage Transfer Learning Method for a Bionic Robotic Fish

Abstract: Directly learning the swimming behaviors of real fish can significantly enhance the swimming performance of bionic robotic fish. This paper presents a novel transfer learning method based on ...
Rochester Institute of Technology

Researchers develop new method for predicting chaos

RIT researchers publish a paper in Nature Scientific Reports on a new tree-based machine learning algorithm used to predict chaos.

Machine learning reveals hidden landscape of robust information storage

In a new study published in Physical Review Letters, researchers used machine learning to discover multiple new classes of ...
North Penn Now

Data Scientist Course Developing Advanced Skills For Intelligent Data Solutions

A data science course is meant to equip learners with a higher level of positions that are founded on the analysis of data, statistics, and machine learning aimed at addressing intricate problems. The ...

Fentanyl or phony? Machine learning algorithm learns to pick out opioid signatures

New forms of fentanyl are created every day. For law enforcement, that poses a challenge: How do you identify a chemical you've never seen before? Researchers at Lawrence Livermore National Laboratory ...