4 papers
Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course
Evelyn Duesterwald, Benjamin Elder, Lilian Ngweta +2
Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains largely unaddressed. When given…
Learning Temporally Consistent Turbulence Between Sparse Snapshots via Diffusion Models
Mohammed Sardar, Małgorzata J. Zimoń, Samuel Draycott +2
We investigate the statistical accuracy of temporally interpolated spatiotemporal flow sequences between sparse, decorrelated snapshots of turbulent flow fields using conditional D…
Interpretable epistemic uncertainty decomposition in sequential generative models via polynomial chaos surrogates
Ramón Nartallo-Kaluarachchi, Shashanka Ubaru, Małgorzata J Zimoń +4
Sequential generative models conditioned on uncertain rewards are central to AI-driven scientific discovery, yet the epistemic uncertainty they inherit from imperfect reward estima…
Predicting Thermodynamics of Liquid Water from Time Series Analysis
Małgorzata J. Zimoń, Fausto Martelli
Thermodynamics, introduced over two centuries ago, remains foundational to our understanding of physical, chemical, biological, and engineering systems. Its principles are traditio…