# Model Recovery at the Edge under Resource Constraints for Physical AI

arXiv: https://arxiv.org/abs/2512.02283 · HTML: https://mlsanity.com/paper/2512.02283/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 35 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 5 of 5)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Modern Koopman Theory for Dynamical Systems](https://mlsanity.com/paper/2102.12086/) (2021)
- [Liquid Time-constant Networks](https://mlsanity.com/paper/2006.04439/) (2020)
- [Sparse identification of nonlinear dynamics for model predictive control in the low-data limit](https://mlsanity.com/paper/1711.05501/) (2017)
- [AI Poincar'e: Machine Learning Conservation Laws from Trajectories](https://mlsanity.com/paper/2011.04698/) (2020)

## Built on by (most cited first, 2 of 2)

- [Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics](https://mlsanity.com/paper/2512.23767/) (2025)
- [EMMA: Extracting Multiple physical parameters from Multimodal Data](https://mlsanity.com/paper/2605.24047/) (2026)

## Abstract (arXiv)

Model Recovery (MR) enables safe, explainable decision making in mission-critical autonomous systems (MCAS) by learning governing dynamical equations, but its deployment on edge devices is hindered by the iterative nature of neural ordinary differential equations (NODEs), which are inefficient on FPGAs. Memory and energy consumption are the main concerns when applying MR on edge devices for real-time operation. We propose MERINDA, a novel FPGA-accelerated MR framework that replaces iterative solvers with a parallelizable neural architecture equivalent to NODEs. MERINDA achieves nearly 11x lower DRAM usage and 2.2x faster runtime compared to mobile GPUs. Experiments reveal an inverse relationship between memory and energy at fixed accuracy, highlighting MERINDA's suitability for resource-constrained, real-time MCAS.