Score: 0

Weight Space Representation Learning with Neural Fields

Published: December 1, 2025 | arXiv ID: 2512.01759v1

By: Zhuoqian Yang, Mathieu Salzmann, Sabine Süsstrunk

Potential Business Impact:

Makes AI create better pictures and understand data.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

In this work, we investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods.

Page Count
24 pages

Category
Computer Science:
Machine Learning (CS)