International Robotic Safety Conference 2025: Key Takeaways Shaping the Future of Safe Automation

The International Robotic Safety Conference highlighted how safety requirements are evolving within one of the ...
IEEE

Towards Universal Performance Modeling for Machine Learning Training on Multi-GPU Platforms

Abstract: Characterizing and predicting the training performance of modern machine learning (ML) workloads on compute systems with compute and communication spread between CPUs, GPUs, and network ...
IEEE

A Comparative Review: Research in Safety and Sustainability of Carbon Nanomaterials Without and With Machine Learning Assistance

Abstract: In recent years, the rapid development of nanomaterials and nanoproducts has led to their widespread application in energy, aerospace, agriculture, industry, and biomedicine. However, carbon ...
GitHub

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning

As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forgetting specific ...
Los Angeles Times

Resource Guarding Is Common Dog Behavior. It Still Needs Your Early Intervention.

This is read by an automated voice. Please report any issues or inconsistencies here. You’re in the kitchen, moving on autopilot. Maybe you’re rinsing a plate or maybe you’re halfway through stepping ...