Skip to main content

News

Software Highlight: AstraAI Masters the Complex Rules of Scientific HPC Software

A flowchart outlining the system architecture for AstraAI. The process begins on the left with a natural language user prompt, which is passed to an LLM for user intent extraction utilizing run-time tools like Hugging Face, Llama.cpp, or Ollama. The workflow then splits into two parallel processes: Retrieval Augmented Generation to extract relevant code chunks, and Abstract Syntax Tree code structure extraction utilizing Clang tools like intercept_build and clang-query. The outputs from these two processes are merged into a final prompt that includes the original user prompt, the RAG chunks, and the structure information. This final prompt is sent to an LLM for code generation, which ultimately leads to AST-safe code editing featuring GitHub conflict-style markers.

New MatterChat Model Helps AI to ‘See’ the Language of Science

A conceptual diagram for "MatterChat: A Structure-Aware Multimodal LLM for Materials." The graphic shows a visual data flow starting from a 3D atomic structure on the left, passing through a bottleneck labeled "Bridge Model," and feeding into a digital interface labeled "LLM." The LLM interface lists various materials science terms like structure, property, synthesis, and stability, with a glowing AI brain floating on the far right.

OmniLearned Foundation Model Shows Promise Across Disciplines

Technical image of a hadronic jet
Computing Sciences logo

Connect

Our Organization