weight-space-learning

Official PyTorch Implementation for the "Recovering the Pre-Fine-Tuning Weights of Generative Models" paper (ICML 2024).

Official PyTorch Implementation for the "Unsupervised Model Tree Heritage Recovery" paper (ICLR 2025).

Code Repository for the ICML 2024 paper: "Towards Scalable and Versatile Weight Space Learning".

Code Repository for the NeurIPS 2022 paper: "Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights".

Official PyTorch Implementation for the "Learning on Model Weights using Tree Experts" paper (CVPR 2025).

Code Repository for the CVPR 2026 paper: "Learning Geospatial Representations from Models, not Data".

An official implementation of ProbeGen

ICML'26: Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion

Research code: parameter symmetry and weight-space learning on sine-network implicit neural representations.

[ICLR 2026] Weight Space Representation Learning on Diverse NeRF Architectures

SANE backbone trained on multiple model zoos.