SEARCH · Search NASA

Results for “large language model”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 397 records · Page 22

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Chemical classification program synthesis using generative artificial intelligence

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

Artificial Intelligence↗

DOE OSTI2026

Genomic Language model for Annotation of Repetitive Elements (GLARE) v1.0

GLARE (Genomic Language model for Annotation of Repetitive Elements) is a tool that classifies transposable elements (TEs)—the mobile, repetitive DNA sequences that make up large fractions of eukaryotic genomes. GLARE fine-tunes the NTv3-650M genomic language model on a harmonized collection of curated TE sequences from the PanTEon and Repbase reference databases, assigning each input sequence to one of 11 orders and 32 superfamilies in a Wicker-compatible taxonomy. Features. From nucleotide FASTA input, GLARE outputs per-sequence predictions, class summaries, composition figures, and an annotated FASTA. It provides calibrated confidence scores with optional abstention and runs on CPU or GPU. Uses. GLARE serves as a classification component in genome-annotation pipelines, downstream of TE discovery, supporting genome annotation and comparative and evolutionary genomics. Advantages. GLARE is the first repeat-element classifier to leverage a pretrained genomic language model. Combined with multi-database training, this approach outperformed all nine classifiers in the PanTEon benchmark, generalized better to unseen taxonomic clades, and remained robust to sequence orientation—a common failure mode of existing tools.

Bruna, Tomas [Lawrence Berkeley National Laborator↗

DOE OSTI2026

Agentic artificial intelligence for multistage physics experiments at a large-scale user facility particle accelerator

We present a language-model-driven agentic artificial intelligence (AI) system to autonomously execute multistage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by 2 orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

Accelerator/storage ring control systems↗

DOE OSTI2026

System-Level Integration of Modular Language Models for Real-Time Risk Assessment in Third-Party Risk Management Systems

Large enterprises typically rely on dedicated teams to govern and implement security measures throughout their supply chains, ensuring compliance with enterprise security procedures. There is a significant reliance on Third-Party Risk Management (TPRM) platforms, which often require complete, highly structured information from potential vendors. The review and compliance assurance processes are time- and labor intensive, often requiring several rounds of review between the supply chain security risk management teams, business users, and potential vendors, leading to delays in the supply chain processing and consumer experience. Significant challenges in the risk management paradigm include handling unstructured data in various formats and providing real-time feedback to users to reduce the required review time. This paper presents a novel solution to these challenges. A modular multi-step system architecture is proposed using advances in language processing, specifically for unstructured responses and provides real-time feedback (i.e., 3 seconds) so that users can improve their responses before the TPSRM team review. This novel system architecture will increase information accuracy and significantly reduce time and labor during the review process.

99 - GENERAL AND MISCELLANEOUS↗

NASA NTRS1981

Pitfalls and guidelines for the numerical evaluation of moderate-order system frequency response

The design and evaluation of a feedback control system via frequency response methods relies heavily upon numerical methods. In application, one can usually develop low order simulation models which for the most part are devoid of numerical problems. However, when complex feedback interactions, for example, between instrument control systems and their flexible mounting structure, must be evaluated, simulation models become moderate to large order and numerical problems become common. A large body of relevant numerical error analysis literature is summarized in a large language understandable to nonspecialists. The intent is to provide engineers using simulation models with an engineering feel for potential numerical problems without getting intertwined in the complexities of the associated mathematical theory. Guidelines are also provided by suggesting alternate state of the art methods which have good numerical evaluation characteristics.

Frisch, H. P.↗

NASA NTRS1995

Formal methods in the design of Ada 1995

Formal, mathematical methods are most useful when applied early in the design and implementation of a software system--that, at least, is the familiar refrain. I will report on a modest effort to apply formal methods at the earliest possible stage, namely, in the design of the Ada 95 programming language itself. This talk is an 'experience report' that provides brief case studies illustrating the kinds of problems we worked on, how we approached them, and the extent (if any) to which the results proved useful. It also derives some lessons and suggestions for those undertaking future projects of this kind. Ada 95 is the first revision of the standard for the Ada programming language. The revision began in 1988, when the Ada Joint Programming Office first asked the Ada Board to recommend a plan for revising the Ada standard. The first step in the revision was to solicit criticisms of Ada 83. A set of requirements for the new language standard, based on those criticisms, was published in 1990. A small design team, the Mapping Revision Team (MRT), became exclusively responsible for revising the language standard to satisfy those requirements. The MRT, from Intermetrics, is led by S. Tucker Taft. The work of the MRT was regularly subject to independent review and criticism by a committee of distinguished Reviewers and by several advisory teams--for example, the two User/Implementor teams, each consisting of an industrial user (attempting to make significant use of the new language on a realistic application) and a compiler vendor (undertaking, experimentally, to modify its current implementation in order to provide the necessary new features). One novel decision established the Language Precision Team (LPT), which investigated language proposals from a mathematical point of view. The LPT applied formal mathematical analysis to help improve the design of Ada 95 (e.g., by clarifying the language proposals) and to help promote its acceptance (e.g., by identifying a verifiable subset that would meet the needs of safety-critical applications). The first LPT project, which ran from the fall of 1990 unti the end of 1992, produced studies of several language issues: optimization, sharing and storage, tasking and protected records, overload resolution, the floating point model, distribution, program erros, and object-oriented programming. The second LPT project, in 1994, formally modeled the dynamic semantics of a large part of the (almost) final language definition, looking especially for interactions between language features.

Guaspari, David↗

DOE OSTI2025

A case study in contrastive learning information combination: Application to technical forensics of additive manufacturing filament source identification

Combination of information from disparate data sources into a single decision is a core challenge in many fields, including the field of technical forensics. Technical forensics (TF) utilizes technical characterization of questioned samples to determine properties of that sample; these properties are then used to infer information of forensic interest, such as provenance, age, or attribution. TF is utilized in traditional forensic applications, such as the attribution of material fragments from an explosive, and in nuclear forensic applications, such as the attribution of actinides which have been interdicted out of regulatory control. The challenge of combining information from disparate sources, described alternately by many terms including “Data Fusion” and “Data Integration”, is exacerbated in the technical forensics domain due to at least two factors: the challenge of interpreting each information source singularly, and the relatively small data set sizes available. Extensive literature exists attempting to combine technical forensics information sources, both in manual and automated processes. These attempts are often bespoke to the specific information sources (such as the bi-, tri-, or quad-isotope chart (Moody, Grant, and Hutcheon 2005)), with some emerging examples of simple early- and late- fusion (, respectively). Simultaneous to the information combination efforts described in the previous paragraph, the field of natural language processing attempted (and largely succeeded) in combining information from multiple non-technical information sources. The ecosystem of “multi-modal” language models, which can take text and images as input, and generate text and images as output, became large and diverse by 2025 (Khan et al. 2025). In a generalized sense, many of these methods are trained by learning neural networks which can convert raw text or images into a vector of numbers describing the text or image, hereafter called “embeddings” and the neural networks performing the conversion are called “embedders”. By using a separate embedder for text and images, finding coincident text and images (such as images with their captions), and optimizing the parameters of the embedders such that the embeddings for the text and the image are similar, the field has found a bridge between text and images (Girdhar et al. 2023). It is the contention of the authors of this report that this insight is not limited to text and images but instead can be extended to any modality which can be found coincidently. The subject of the rest of this report is the application of this method to example multi-modal technical forensic data. Some details about the data used in this report are not appropriate for this report, and are included in a companion report (PNNL-38669).

36 MATERIALS SCIENCE↗

DOE OSTI2024

Pretraining Billion-Scale Geospatial Foundational Models on Frontier

As AI workloads increase in scope, generalization capability becomes challenging for small task-specific models and their demand for large amounts of labeled training samples increases. On the contrary, Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning and have been shown to adapt to various tasks with minimal fine-tuning. Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators. Current satellite constellations collect 100+TBs of data a day, resulting in images that are billions of pixels and multimodal in nature. Such geospatial data poses unique challenges opening up new opportunities to develop FMs. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. We studied from end-to-end the performance and impact in the solution by scaling the model size. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy when comparing a 100M parameter model. Moreover, we detail performance experiments on the Frontier supercomputer, America's first exascale system, where we study different model and data parallel approaches using PyTorch's Fully Sharded Data Parallel library. Specifically, we study variants of the Vision Transformer architecture (ViT), conducting performance analysis for ViT models with size up to 15B parameters. By discussing throughput and performance bottlenecks under different parallelism configurations, we offer insights on how to leverage such leadership-class HPC resources when developing large models for geospatial imagery applications.

Tsaris, Aristeidis (aris)↗

NASA NTRS1991

VHDL simulation with access to transistor models

Hardware description languages such as VHDL have evolved to aid in the design of systems with large numbers of elements and a wide range of electronic and logical abstractions. For high performance circuits, behavioral models may not be able to efficiently include enough detail to give designers confidence in a simulation's accuracy. One option is to provide a link between the VHDL environment and a transistor level simulation environment. The coupling of the Vantage Analysis Systems VHDL simulator and the NOVA simulator provides the combination of VHDL modeling and transistor modeling.

Gibson, J.↗

NASA NTRS2018

Towards a Unified View of Modeling and Programming (ISoLA 2018 Track Introduction)

The article provides an introduction to the track: Towards a Uniﬁed View of Modeling and Programming, organized by the authors of this paper as part of ISoLA 2018: the 8th International Symposium On Leveraging Applications of Formal Methods, Veriﬁcation and Validation. A total of 19 researchers were invited to present their views on the two questions: what are the commonalities between modeling and programming languages, and should we strive towards a uniﬁed view of modeling and programming? The idea behind the track, which is a continuation of a similar track at ISoLA 2016, emerged as a result of experiences gathered in the three ﬁelds: formal methods, model-based software engineering, and programming languages, and from the observation that these technologies share a large common part, to the extent where one may ask, does the following equation hold: modeling = programming?

Steffen, Bernhard↗

DOE OSTI2025

Autogenerating a Domain-Specific Question-Answering Data Set from a Thermoelectric Materials Database to Enable High-Performing BERT Models

We present a method for autogenerating a large domain-specific question-answering (QA) dataset from a thermoelectric materials database. We show that a small language model, BERT, once fine-tuned on this automatically generated dataset of 99,757 QA pairs about thermoelectric materials, affords better performance in the field of thermoelectric materials compared to a BERT model fine-tuned on the generic English-language QA data set, SQuAD-v2. We further show that mixing the two data sets (ours and SQuAD-v2), which have significantly different syntactic and semantic scopes, allows the BERT model to achieve even better performance. The best-performing BERT model fine-tuned on the mixed data set outperforms the models fine-tuned on the other two data sets by scoring an exact match of 67.93% and an F1 score of 72.29% when evaluated on our test data set. This has important implications as it demonstrates the ability to realize high-performing small language models, with modest computational resources, empowered by domain-specific materials data sets which can be generated according to our method.

biological databases↗

DOE OSTI2024

Dynamic Model of Back-to-Back Converter for System Level Phasor Simulation

The power system is expected to evolve rapidly with increasing deployment of power electronic interface and conditioning systems, microgrids, and hybrid AC/DC grids. Among power electronic systems, back-to-back (BTB) converters can be a powerful interface to integrate microgrids and networked microgrids. However, in system level dynamic simulations for synchronous machine dominated system with BTB converters, a detailed electromagnetic sinusoidal models is not warranted as these simulations are focused on electromechanical transients. This paper focus on developing a simple phasor model for back- to-back converters that can be easily integrated into powerflow solvers to facilitate large-scale power system simulations. The model is implemented using C++ language and integrated into GridLAB-D software as a potential new capability. The GridLAB-D phasor domain model is validated against the electromagnetic transient (EMT) simulation of the detailed switching model. Simulation results show that the phasor model successfully captures the dominant dynamics of the converters.

Mahmood, Hisham↗

NASA NTRS2006

ADGS-2100 Adaptive Display and Guidance System Window Manager Analysis

Recent advances in modeling languages have made it feasible to formally specify and analyze the behavior of large system components. Synchronous data flow languages, such as Lustre, SCR, and RSML-e are particularly well suited to this task, and commercial versions of these tools such as SCADE and Simulink are growing in popularity among designers of safety critical systems, largely due to their ability to automatically generate code from the models. At the same time, advances in formal analysis tools have made it practical to formally verify important properties of these models to ensure that design defects are identified and corrected early in the lifecycle. This report describes how these tools have been applied to the ADGS-2100 Adaptive Display and Guidance Window Manager being developed by Rockwell Collins Inc. This work demonstrates how formal methods can be easily and cost-efficiently used to remove defects early in the design cycle.

Whalen, Mike W.↗

NASA NTRS1991

Hybrid automated reliability predictor integrated work station (HiREL)

The Hybrid Automated Reliability Predictor (HARP) integrated reliability (HiREL) workstation tool system marks another step toward the goal of producing a totally integrated computer aided design (CAD) workstation design capability. Since a reliability engineer must generally graphically represent a reliability model before he can solve it, the use of a graphical input description language increases productivity and decreases the incidence of error. The captured image displayed on a cathode ray tube (CRT) screen serves as a documented copy of the model and provides the data for automatic input to the HARP reliability model solver. The introduction of dependency gates to a fault tree notation allows the modeling of very large fault tolerant system models using a concise and visually recognizable and familiar graphical language. In addition to aiding in the validation of the reliability model, the concise graphical representation presents company management, regulatory agencies, and company customers a means of expressing a complex model that is readily understandable. The graphical postprocessor computer program HARPO (HARP Output) makes it possible for reliability engineers to quickly analyze huge amounts of reliability/availability data to observe trends due to exploratory design changes.

Bavuso, Salvatore J.↗

DOE OSTI2024

Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images

Machine learning models are known to be vulnerable to adversarial attacks, but prior works have mostly focused on single-modalities. With the rise of large multi-modal models (LMMs) like CLIP, which combine vision and language capabilities, new vulnerabilities have emerged. However, these multimodal targeted attacks aim to completely change the model's output to what the adversary wants. In many realistic scenarios, an adversary might seek to make only subtle modifications to the output, so that the changes go unnoticed by downstream models or even by humans. We introduce Hiding-in-Plain-Sight (HiPS) attacks, a novel class of adversarial attacks that subtly modifies model predictions by selectively concealing target object(s), as if the target object was absent from the scene. We propose two HiPS attack variants, HiPS-cls and HiPS-cap, and demonstrate their effectiveness in transferring to downstream image captioning models, such as CLIP-Cap, for targeted object removal from image captions.

Daw, Arka [ORNL] (ORCID:0009000633191271)↗

NASA NTRS1990

Analytical learning and term-rewriting systems

Analytical learning is a set of machine learning techniques for revising the representation of a theory based on a small set of examples of that theory. When the representation of the theory is correct and complete but perhaps inefficient, an important objective of such analysis is to improve the computational efficiency of the representation. Several algorithms with this purpose have been suggested, most of which are closely tied to a first order logical language and are variants of goal regression, such as the familiar explanation based generalization (EBG) procedure. But because predicate calculus is a poor representation for some domains, these learning algorithms are extended to apply to other computational models. It is shown that the goal regression technique applies to a large family of programming languages, all based on a kind of term rewriting system. Included in this family are three language families of importance to artificial intelligence: logic programming, such as Prolog; lambda calculus, such as LISP; and combinatorial based languages, such as FP. A new analytical learning algorithm, AL-2, is exhibited that learns from success but is otherwise quite different from EBG. These results suggest that term rewriting systems are a good framework for analytical learning research in general, and that further research should be directed toward developing new techniques.

Laird, Philip↗

NASA NTRS1991

Simulation-based instruction of technical skills

A rapid intelligent tutoring development system (RAPIDS) was developed to facilitate the production of interactive, real-time graphical device models for use in instructing the operation and maintenance of complex systems. The tools allowed subject matter experts to produce device models by creating instances of previously defined objects and positioning them in the emerging device model. These simulation authoring functions, as well as those associated with demonstrating procedures and functional effects on the completed model, required no previous programming experience or use of frame-based instructional languages. Three large simulations were developed in RAPIDS, each involving more than a dozen screen-sized sections. Seven small, single-view applications were developed to explore the range of applicability. Three workshops were conducted to train others in the use of the authoring tools. Participants learned to employ the authoring tools in three to four days and were able to produce small working device models on the fifth day.

Towne, Douglas M.↗

NASA NTRS2024

AI Foundation Model for Heliophysics: Applications, Design, and Implementation

Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications. Foundation models (FMs), which are pre-trained on a large-scale datasets, form the basis fora variety of downstream tasks. These models, especially those based on trans-formers in vision and language, show exceptional potential for adapting to a wide range of downstream applications. In this paper, we provide our perspective on the criteria for designing a FM for heliophysic and associated challenges and applications using the Solar Dynamics Observatory (SDO) dataset. We believe that this is the first study to design a foundation model in the domain of heliophysics.

Sujit Roy↗