SEARCH · Search NASA
Results for “language”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Fairness and social bias quantification in Large Language Models for sentiment analysis
Not Available
DR-BERT: A protein language model to annotate disordered regions
Not Available
RNA language models predict mutations that improve RNA function
Structured RNA lies at the heart of many central biological processes, from gene expression to catalysis. RNA structure prediction is not yet possible due to a lack of high-quality reference data associated with organismal phenotypes that could inform RNA function. We present GARNET (Gtdb Acquired RNa with Environmental Temperatures), a new database for RNA structural and functional analysis anchored to the Genome Taxonomy Database (GTDB). GARNET links RNA sequences to experimental and predicted optimal growth temperatures of GTDB reference organisms. Using GARNET, we develop sequence- and structure-aware RNA generative models, with overlapping triplet tokenization providing optimal encoding for a GPT-like model. Leveraging hyperthermophilic RNAs in GARNET and these RNA generative models, we identify mutations in ribosomal RNA that confer increased thermostability to the Escherichia coli ribosome. The GTDB-derived data and deep learning models presented here provide a foundation for understanding the connections between RNA sequence, structure, and function.
Author Correction: A universal language for finding mass spectrometry data patterns
Correction to: Nature Methodshttps://doi.org/10.1038/s41592-025-02660-z, published online 12 May 2025. This article was originally published under standard Springer Nature license (© The Author(s), under exclusive licence to Springer Nature America, Inc.). It is now available as an open-access paper under a Creative Commons Attribution 4.0 International license, © The Author(s). The error has been corrected in the HTML and PDF versions of the article.
Information extraction from historical well records using a large language model
Not Available
Solving tricky quantum optics problems with assistance from large language models
The capabilities of modern artificial intelligence (AI) as a “scientific collaborator” are explored by engaging it with three nuanced problems in quantum optics: state populations in optical pumping, resonant transitions between decaying states (the Burshtein effect), and degenerate mirrorless lasing. Through iterative dialogue, the authors observe that AI models–when prompted and corrected–can reason through complex scenarios, refine their answers, and provide expert-level guidance, closely resembling the interaction with an adept colleague. The findings highlight that AI can democratize access to sophisticated modeling and analysis, shifting the focus in scientific practice from technical mastery to the generation and testing of ideas, and reducing the time for completing research tasks from days to minutes.
ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning
ProtAgents is a de novo protein design platform based on multimodal LLMs, where distinct AI agents with expertise in knowledge retrieval, protein structure analysis, physics-based simulations, and results analysis tackle tasks in a dynamic setting.
Mining experimental data from materials science literature with large language models: an evaluation study
Not Available
Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysis
Explore the source record for details and available documents.
ESGF-Assistant: A Domain-Specific Large Language Model for Navigating Earth System Data
Explore the source record for details and available documents.
Do Research Software Engineers and Software Engineering Researchers Speak the Same Language?
Anecdotal evidence suggests that research software engineers (RSEs) and software engineering researchers (SERs) often use different terminologies for similar concepts, creating communication challenges. To better understand these divergences, we have started investigating how software engineering fundamentals from the SER community are interpreted within the RSE community, identifying aligned concepts, knowledge gaps, and areas for potential adaptation. In conclusion, our preliminary findings reveal opportunities for mutual learning and collaboration, and our systematic methodology for terminology mapping provides a foundation for a crowdsourced extension and validation in the future.
ION: Navigating the HPC I/O Optimization Journey using Large Language Models
None
FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving
Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent replicas, while tensor parallelism (TP) reduces per-request latency and pools memory for long-context inference. However, existing serving stacks typically commit to a static parallelism configuration at deployment; adapting to bursts, priorities, or long-context requests is often disruptive and slow. We present Flying Serving, a vLLM-based system that enables online DP-TP switching without restarting engine workers. Flying Serving makes reconfiguration practical by virtualizing the state that would otherwise force data movement: (i) a zero-copy Model Weights Manager that exposes TP shard views on demand, (ii) a KV Cache Adaptor that preserves request KV state across DP/TP layouts, (iii) an eagerly initialized Communicator Pool to amortize collective setup, and (iv) a deadlock-free scheduler that coordinates safe transitions under execution skew. Across three popular LLMs and realistic serving scenarios, Flying Serving improves performance by up to 4.79 × under high load and 3.47 × under low load while supporting latency- and memory-driven requests.