# Fast Amortized Fitting of Scientific Signals Across Time and Ensembles via Transferable Neural Fields

arXiv: https://arxiv.org/abs/2604.19979 · HTML: https://mlsanity.com/paper/2604.19979/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Learned Initializations for Optimizing Coordinate-Based Neural Representations](https://mlsanity.com/paper/2012.02189/) (2020)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning](https://mlsanity.com/paper/2412.00568/) (2024)
- [Transformers as Meta-Learners for Implicit Neural Representations](https://mlsanity.com/paper/2208.02801/) (2022)
- [NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling](https://mlsanity.com/paper/2212.14593/) (2022)
- [DINER: Disorder-Invariant Implicit Neural Representation](https://mlsanity.com/paper/2211.07871/) (2022)
- [Interactive Volume Visualization via Multi-Resolution Hash Encoding based Neural Representation](https://mlsanity.com/paper/2207.11620/) (2022)
- [Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualization](https://mlsanity.com/paper/2308.02494/) (2023)
- [Learning Transferable Features for Implicit Neural Representations](https://mlsanity.com/paper/2409.09566/) (2024)
- [3D-Spatiotemporal Forecasting the Expansion of Supernova Shells Using Deep Learning toward High-Resolution Galaxy Simulations](https://mlsanity.com/paper/2302.00026/) (2023)
- [Fit Pixels, Get Labels: Meta-learned Implicit Networks for Image Segmentation](https://mlsanity.com/paper/2510.04021/) (2025)
- [Surrogate Modeling for Computationally Expensive Simulations of Supernovae in High-Resolution Galaxy Simulations](https://mlsanity.com/paper/2311.08460/) (2023)
- [F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding](https://mlsanity.com/paper/2507.03836/) (2025)
- [Adaptive Multi-Resolution Encoding for Interactive Large-Scale Volume Visualization through Functional Approximation](https://mlsanity.com/paper/2409.00184/) (2024)

## Abstract (arXiv)

Neural fields, also known as implicit neural representations (INRs), offer a powerful framework for modeling continuous geometry, but their effectiveness in high-dimensional scientific settings is limited by slow convergence and scaling challenges. In this study, we extend INR models to handle spatiotemporal and multivariate signals and show how INR features can be transferred across scientific signals to enable efficient and scalable representation across time and ensemble runs in an amortized fashion. Across controlled transformation regimes (e.g., geometric transformations and localized perturbations of synthetic fields) and high-fidelity scientific domains-including turbulent flows, fluid-material impact dynamics, and astrophysical systems-we show that transferable features improve not only signal fidelity but also the accuracy of derived geometric and physical quantities, including density gradients and vorticity. In particular, transferable features reduce iterations to reach target reconstruction quality by up to an order of magnitude, increase early-stage reconstruction quality by multiple dB (with gains exceeding 10 dB in some cases), and consistently improve gradient-based physical accuracy.