Physics2Weight: LLMs Generate Neural Network Weights Directly From Physical Laws
A new arXiv paper, Physics2Weight, presents a method using large language models to directly generate neural network architectures and weights from physical laws, extending weight-space programming without gradient-based training.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-11 05:00 · arXiv cs.AI
Physics2Weight: Direct Neural Network Architecture and Weight Generation from Physical Laws Using Large Language Models