IEEE

Effective and Robust Adversarial Training Against Data and Label Corruptions

Abstract: Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in ...
IEEE

A Weighted Co-Training Framework for Emotion Recognition Based on EEG Data Generation Using Frequency-Spatial Diffusion Transformer

Abstract: Emotion recognition based on EEG signals has been a challenging task. The acquisition of EEG signals is complex, time-consuming, and has a high overhead. Artificial Intelligence Generated ...
news.bloomberglaw

xAI Sues California Attorney General Over Training Data Law (1)

Elon Musk’s artificial intelligence company xAI filed a federal lawsuit alleging a California law requiring AI companies to reveal their training data is an unconstitutional “trade-secrets-destroying ...
Microsoft

VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus

We introduce VeriStruct, a novel framework that extends AI-assisted automated verification from single functions to more complex data structure modules in Verus. VeriStruct employs a planner module to ...
Interesting Engineering

China opens robot school to prep humanoids for factory tasks and home chores

China has opened an unusual new school aimed at preparing humanoid robots for a wide range of tasks, from working on factory floors to helping out at home and in public spaces. The Phase II Beijing ...
GitHub

Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect Detection

Official implementation of the paper Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect Detection accepted at the 21st International Conference ...