Intelligence Ars Technica
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
"This is day one for cybersecurity in the age of agents," Hugging Face CEO says.
Full corpus search
Find the frequency
5 matches for “ai-alignment”
Research arXiv
Variance-reduced Domain Adaptation using Paired Sampling
Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA). However, high variance in these losses has been shown to undermine their effectiveness in minibatch…
Research arXiv
UnDA: Unpaired Domain Alignment for Cross-Modal Knowledge Transfer in Medical Imaging
Multimodal based approaches often outperform single modality approaches in downstream tasks as the different modalities provide complementary information, yet acquiring paired clinical data remains a significant challenge in real world scenarios. While…
Research arXiv
Online Variance Reduction for Domain Adaptation on Streaming Data
This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions. Although various offline SVR algorithms for these losses have been proposed, these are incompatible…
Research arXiv
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this…