This paper provides an in-depth examination of the concept of semantic diffusion as a complementary instrument to large language models (LLMs) for design applications. Conventional LLMs and diffusion models fail to induce a convergent, iterative refinement process: each invocation of the diffusion mechanism spawns a new stochastic cycle, so successive outputs do not relate to prior ones and convergence toward a desired design is not guaranteed. The proposed hybrid framework - "LLM + semantic diffusion" - resolves this limitation by enforcing an approximately convergent search procedure, thereby formally addressing the problem of localized design refinement.
@article{arxiv.2505.09283,
title = {A Note on Semantic Diffusion},
author = {Alexander P. Ryjov and Alina A. Egorova},
journal= {arXiv preprint arXiv:2505.09283},
year = {2025}
}