IEEE

Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks

Abstract: Sharpness-Aware Minimization (SAM) has proven highly effective in improving model generalization in machine learning tasks. However, SAM employs a fixed hyperparameter associated with the ...
IEEE

AoI Minimization for Air–Ground Integrated Sensing and Communication Networks With Jamming Attack

Abstract: Air-ground integrated sensing and communication (AG-ISAC) networks utilize unmanned aerial vehicles (UAVs) equipped with ISAC units as aerial platforms in next-generation wireless systems, ...
Hacker

Beyond Consent: How Data Minimization Can Actually Work in Open Banking

I am a Research Scientist and Technical Leader in cybersecurity and blockchain. I am a Research Scientist and Technical Leader in cybersecurity and blockchain. Technical Leader and Research Scientist, ...
GitHub

RENT: Reinforcement Learning via Entropy Minimization

RENT is an unsupervised method for training reasoning LLMs by minimizing entropy. We demonstrate on a variety of datasets and models that RENT improves model performance without using any ground truth ...