---
datasets:
- frallebini/gmnerf
license: mit
pipeline_tag: graph-ml
tags:
- weight-space-learning
- nerf
- graph-metanetwork
---

# Weight Space Representation Learning on Diverse NeRF Architectures (ICLR 2026)

[![paper](https://img.shields.io/badge/arxiv-paper-darkred?logo=arxiv)](https://arxiv.org/abs/2502.09623)
[![code](https://img.shields.io/badge/github-code-blue?logo=github)](https://github.com/CVLAB-Unibo/gmnerf)
[![datasets](https://img.shields.io/badge/huggingface-datasets-teal?logo=huggingface)](https://huggingface.co/datasets/frallebini/gmnerf)

![teaser](https://cvlab-unibo.github.io/gmnerf/static/images/teaser.svg)

This repository contains the models for the paper [Weight Space Representation Learning on Diverse NeRF Architectures](https://arxiv.org/abs/2502.09623). The paper proposes a framework that is capable of processing NeRFs with diverse architectures (MLPs, tri-planes, and hash tables) by training a graph metanetwork to obtain an architecture-agnostic latent space.

## Repo content

- `l_con/best.pt`: \\(\mathcal{L}_\text{C}\\) model
- `l_rec/best.pt`: \\(\mathcal{L}_\text{R}\\) model
- `l_rec_con/best.pt`: \\(\mathcal{L}_\text{R+C}\\) model
- `llana`: [LLaNA](https://andreamaduzzi.github.io/llana) model trained on \\(\mathcal{L}_\text{R+C}\\) embeddings

## Cite us

If you find our work useful, please cite us:

```bibtex
@inproceedings{ballerini2026weight,
  title = {Weight Space Representation Learning on Diverse {NeRF} Architectures},
  author = {Ballerini, Francesco and Zama Ramirez, Pierluigi and Di Stefano, Luigi and Salti, Samuele},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year = {2026}
}
```