Science

A new method dramatically speeds up the process of identifying vulnerabilities in large language models, offering a more practical approach to AI security.

Researchers have developed a novel diffusion model that tackles the challenge of missing data in sequential recommendation systems, improving accuracy and personalization.

A new technique allows developers to remove sensitive information from AI models without needing access to the original training data.

Researchers have developed a novel theoretical framework for understanding how noise affects the complex dynamics of recurrent neural networks.

A new generative model tackles the challenge of identifying objects in synthetic aperture radar (SAR) imagery when labeled training data is scarce.

New research demonstrates that combining the power of deep learning with established inventory management principles yields significantly improved performance in perishable goods forecasting.

New research reveals the challenges of ensuring consistent and reliable behavior in AI-powered financial tools, and proposes a framework for rigorous testing.

A new framework leverages reinforcement learning to intelligently prioritize the most valuable data for training object detection models, significantly improving efficiency and accuracy.

A new framework leverages autoregressive modeling and latent spaces to accurately solve complex equations even when only partial observations are available.

Researchers have developed a novel model, Dualformer, that analyzes time series data in both the time and frequency domains to significantly improve long-term prediction accuracy.