Metraipolis › archive › dc_f86bf32e5b11

Conditional Dynamical Systems for Image Generation — arXiv:2608.14961

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14961
License (as archived)
CC0-1.0
Archived
2026-10-19T00:50:44.950Z
SHA-256 of the archived text
4f8bce9cbc57080dcea15685096424698a83b2d867ce74ae8fb8cb5b4bb7b5ea
Stable URL of this page
https://metraipolis.com/documento/dc_f86bf32e5b11

How to cite

Conditional Dynamical Systems for Image Generation — arXiv:2608.14961 — arXiv (en), https://arxiv.org/abs/2608.14961 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f86bf32e5b11 (Metraipolis archive dc_f86bf32e5b11, sha256 4f8bce9cbc57080dcea15685096424698a83b2d867ce74ae8fb8cb5b4bb7b5ea)
BibTeX
@misc{dcf86bf32e5b11,
  title = {Conditional Dynamical Systems for Image Generation — arXiv:2608.14961},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14961},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f86bf32e5b11; sha256 4f8bce9cbc57080dcea15685096424698a83b2d867ce74ae8fb8cb5b4bb7b5ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14961. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image generation is dominated by deep generative models on GPUs, whose computational and energy costs raise sustainability concerns. Emerging non-von Neumann substrates, including quantum, compute-in-memory, photonic, and thermodynamic platforms, promise greater efficiency, yet most work ports conventional neural network architectures onto them and mainly accelerates operations such as matrix multiplication. This does not fully exploit a native capability of many hardware substrates: relaxation toward low-energy states can itself compute at little cost. Building on this primitive, we develop dynamical systems for image generation based on Ising spins and Kuramoto oscillators. The internal states of both models evolve under dynamics with an explicit Lyapunov energy, and a compact decoder renders the final states as images. For conditional generation, we introduce local conditioning: programmed interactions remain fixed, and one class-dependent bias per node reshapes the landscape, avoiding additional reprogramming and calibration costs. On CIFAR-10, the Ising and Kuramoto models reach clean-FID scores of $6.40$ and $5.37$, respectively, with $4096$ nodes. With a CMOS-compatible hardware realization, the dynamical-system core is projected to cost ${\sim}110.6$~nJ per image, and the full computation, even with the decoder on a GPU, outperforms all GPU baselines in latency and energy. These results suggest that energy-descending dynamics on non-von Neumann substrates can serve as generative computation, offering an efficient path beyond GPUs.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-18 in cs.ET).
Categorie arXiv: Emerging Technologies (cs.ET).
Pagina del lavoro: https://arxiv.org/abs/2608.14961 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T00:26:44.324Z dalla pagina https://arxiv.org/catchup/cs.ET/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).