frallebini/gmnerf

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

This repository contains the models for the paper Weight Space Representation Learning on Diverse NeRF Architectures. 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: ${\mathcal{L}}_{\text{C}}\backslash mathcal\{L\}\_\backslash text\{C\}$ model
• l_rec/best.pt: ${\mathcal{L}}_{\text{R}}\backslash mathcal\{L\}\_\backslash text\{R\}$ model
• l_rec_con/best.pt: ${\mathcal{L}}_{\text{R+C}}\backslash mathcal\{L\}\_\backslash text\{R+C\}$ model
• llana: LLaNA model trained on ${\mathcal{L}}_{\text{R+C}}\backslash mathcal\{L\}\_\backslash text\{R+C\}$ embeddings

Cite us

If you find our work useful, please cite us:

@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}
}