10 papers
How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?
Pochinapeddi Sai Bhargav, Nithin Somasekharan, Rohit Sunil Kanchi +2
Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear how different components of di…
Deep Koopman Sensing
Nithin Somasekharan, Yadi Cao, Shaowu Pan
Real-time reconstruction of fluid flows from sparse sensor measurements is important for both physical understanding and flow control. When first-principles models are too expensiv…
Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems
Patrick Emami, Sameera Horawalavithana, Truc Nguyen +11
Large language model-based agents are increasingly deployed as collaborators in scientific discovery yet most current work focuses on the autonomous capabilities of "AI Scientists"…
SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science
Nithin Somasekharan, Youssef Hassan, Shiyao Lin +5
Large Language Models (LLMs) are increasingly deployed as scientific AI as- sistants, and a growing body of benchmarks evaluates their capabilities across knowledge retrieval, reas…
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
Nithin Somasekharan, Rabi Pathak, Manushri Dhanakoti +4
Recent LLM-based agents have closed substantial portions of the scientific discovery loop in software-only machine-learning research, in chemistry, and in biology. Extending the sa…
Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAM
Ling Yue, Nithin Somasekharan, Tingwen Zhang +2
Computational Fluid Dynamics (CFD) is an essential simulation tool in engineering, yet its steep learning curve and complex manual setup create significant barriers. To address the…
CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics
Nithin Somasekharan, Ling Yue, Yadi Cao +6
Large Language Models (LLMs) have demonstrated strong performance across general NLP tasks, but their utility in automating numerical experiments of complex physical system -- a cr…
UniFoil: A Universal Dataset of Airfoils in Transitional and Turbulent Regimes for Subsonic and Transonic Flows
Rohit Sunil Kanchi, Benjamin Melanson, Nithin Somasekharan +2
We present UniFoil, a large publicly available universal airfoil dataset based on Reynolds-averaged Navier-Stokes (RANS) simulations. It contains over 500,000 samples spanning a wi…
Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows
Ling Yue, Nithin Somasekharan, Tingwen Zhang +4
Computational fluid dynamics (CFD) has been the main workhorse of computational physics, yet its steep learning curve and fragmented, multi-stage workflow create significant barrie…
Beyond the Kolmogorov Barrier: A Learnable Weighted Hybrid Autoencoder for Model Order Reduction
Nithin Somasekharan, Shaowu Pan
Representation learning for high-dimensional, complex physical systems aims to identify a low-dimensional intrinsic latent space, which is crucial for reduced-order modeling and mo…