Topic: Natural Language Processing

A new study led by CASC researchers empowers users to interact with the application through natural-language and visual inputs instead of the typical graphic user interface, which can appear daunting for novice users.

LLNL and Amazon Web Services are partnering to leverage the power of AI to enhance operations at the National Ignition Facility.

LLNL participates in the ISC High Performance Conference (ISC24) on June 10–13.

LLNL researchers have posters and workshop papers accepted to the 13th International Conference on Learning Representations on April 24–28.

The February 28 event brought together over 1,400 Department of Energy scientists across multiple sites to explore how cutting-edge AI models could transform scientific research.

Over the next three years, CASC researchers and collaborators will integrate LLMs into HPC software to boost performance and sustainability.

Highlights include ML techniques for computed tomography, a scalable Gaussian process framework, safe and trustworthy AI, and autonomous multiscale simulations.

Presented last fall at a conference, a new approach to software binary analysis incorporates large-scale training data and hierarchical embeddings.

The Generative Unconstrained Intelligent Drug Engineering (GUIDE) program accelerates development of medical countermeasure candidates to redefine biological defense.

In two papers from the 2024 International Conference on Machine Learning, Livermore researchers investigate how LLMs perform under measurable scrutiny.

A novel ML method discovers and predicts key data about networked devices.

Highlights include MFEM community workshops, compiler co-design, HPC standards committees, and AI/ML for national security.