Showing 2026Show all
2 papers · 1 filter
cs.GR2026
GENIE: Gram-Eigenmode INR Editing with Closed-Form Geometry Updates
Samundra Karki, Adarsh Krishnamurthy, Baskar Ganapathysubramanian
Implicit Neural Representations (INRs) provide compact models of geometry, but it is unclear when their learned shapes can be edited without retraining. We show that the Gram opera…
cs.CE2026
Neural Geometry for PDEs: Regularity, Stability, and Convergence Guarantees
Samundra Karki, Adarsh Krishnamurthy, Baskar Ganapathysubramanian
Implicit Neural Representations (INRs) have emerged as a powerful tool for geometric representation, yet their suitability for physics-based simulation remains underexplored. While…