14 papers
When Scientific Cognition Is No Longer Scarce
Nathan DeBardeleben
AI could change which parts of science impede progress. Consider a world in which machine systems are better, faster, and cheaper than people at most scientific work that can be do…
Sim+Real: Joint Simulation-Experiment Training Improves Balanced Prediction in Physical Systems
Mahindra Rautela, Alexander Scheinker, Ayan Biswas +3
Simulation and experimental measurements provide complementary data for learning spatiotemporal physical systems, but standard simulation-to-experiment fine-tuning optimizes only t…
Accountability Asymmetry and Structural Trust in Autonomous AI Systems
Nathan DeBardeleben
Autonomous AI systems (such as AI agents) are increasingly being delegated operational work across scientific-computing infrastructure. Their assignments may begin with preparing a…
Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation
Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben +4
Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying…
An Agentic Orchestration of Atomistic Simulations
Rahul Somasundaram, Adela Habib, Khanh Dang +12
Atomistic simulations are central to materials design, but their execution involves complex, multi-step workflows that require significant human expertise. Here, we present an agen…
DiffUNet^2: Bidirectional Conditional Diffusion for Probabilistic Scientific Spatiotemporal Modeling
Mengdi Chu, Jiaxin Yang, Angus G. Forbes +4
Studying the spatiotemporal evolution of scientific phenomena often relies on costly simulations and experiments. Machine learning-based surrogate models reduce this cost, but most…
In-context learning enables continental-scale subsurface temperature prediction from sparse local observations
Daniel O'Malley, Christopher W. Johnson, Javier E. Santos +10
Continental-scale knowledge of subsurface temperature is limited by the cost and sparsity of borehole measurements, but such information is essential for geothermal resource assess…
PDE foundation model-accelerated inverse estimation of system parameters in inertial confinement fusion
Mahindra Rautela, Alexander Scheinker, Bradley Love +4
PDE foundation models are typically pretrained on large, diverse corpora of PDE datasets and can be adapted to new settings with limited task-specific data. However, most downstrea…
Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading
Mahindra Rautela, Alexander Most, Siddharth Mansingh +9
Most PDE foundation models are pretrained and fine-tuned on fluid-centric benchmarks. Their utility under extreme-loading material dynamics remains unclear. We benchmark out-of-dis…
MORPH: PDE Foundation Models with Arbitrary Data Modality
Mahindra Singh Rautela, Alexander Most, Siddharth Mansingh +6
We introduce MORPH, a modality-agnostic, autoregressive foundation model for partial differential equations (PDEs). MORPH is built on a convolutional vision transformer backbone th…
A Foundation Model for Material Fracture Prediction
Agnese Marcato, Aleksandra Pachalieva, Ryley G. Hill +14
Accurately predicting when and how materials fail is critical to designing safe, reliable structures, mechanical systems, and engineered components that operate under stress. Yet,…
VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization
Ayan Biswas, Terece L. Turton, Nishath Rajiv Ranasinghe +7
We present VizGenie, a self-improving, agentic framework that advances scientific visualization through large language model (LLM) by orchestrating of a collection of domain-specif…
URSA: The Universal Research and Scientific Agent
Michael Grosskopf, Nathan Debardeleben, Russell Bent +10
Large language models (LLMs) have moved far beyond their initial form as simple chatbots, now carrying out complex reasoning, planning, writing, coding, and research tasks. These s…
Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering
Landon Dyken, Andres Sewell, Will Usher +3
Visualizing the large-scale datasets output by HPC resources presents a difficult challenge, as the memory and compute power required become prohibitively expensive for end user sy…