news

Jul 01, 2026 First-author paper on subspace optimization for physics-informed learning submitted to IEEE Transactions on Neural Networks and Learning Systems.
May 15, 2026 New preprint posted: “Local Inverse Geometry Can Be Amortized.” arXiv:2605.13068.
Dec 01, 2025 Presented “Deceptron: Learned Local Inverses for Fast and Stable Physics Inversion” at the NeurIPS Machine Learning for Physical Sciences Workshop in San Diego on 6th December, 2025.
Nov 07, 2025 Met with the Vice Chancellor of VNSGU Surat, Dr. Kishorsinh N. Chavda, who conveyed wishes for my research work and NeurIPS ML4PS presentation.