5 papers
Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis
Vansh Sharma, Venkat Raman
Agentic large language models are proposed as autonomous code generators for scientific computing, yet their reliability in high-stakes problems remains unclear. Developing computa…
AutoHood3D: A Multi-Modal Benchmark for Automotive Hood Design and Fluid-Structure Interaction
Vansh Sharma, Harish Jai Ganesh, Maryam Akram +2
This study presents a new high-fidelity multi-modal dataset containing 16000+ geometric variants of automotive hoods useful for machine learning (ML) applications such as engineeri…
Steering Conceptual Bias via Transformer Latent-Subspace Activation
Vansh Sharma, Venkat Raman
This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were…
An AMReX-based Compressible Reacting Flow Solver for High-speed Reacting Flows relevant to Hypersonic Propulsion
Shivank Sharma, Ral Bielawski, Oliver Gibson +8
This work presents a comprehensive framework for the efficient implementation of finite-volume-based reacting flow solvers, specifically tailored for high speed propulsion applicat…
A Machine Learning Based Approach for Statistical Analysis of Detonation Cells from Soot Foils
Vansh Sharma, Michael Ullman, Venkat Raman
This study presents a novel algorithm based on machine learning (ML) for the precise segmentation and measurement of detonation cells from soot foil images, addressing the limitati…