Metraipolis › archive › dc_dc680b4bc069

Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning — arXiv:2608.14706

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14706
License (as archived): CC0-1.0
Archived: 2026-10-18T17:52:09.504Z
SHA-256 of the archived text: 8d856af99e347668d71a947278cbc45cbfc1c1b148e39343cef3edf2817a4afc
Stable URL of this page: https://metraipolis.com/documento/dc_dc680b4bc069

How to cite

Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning — arXiv:2608.14706 — arXiv (en), https://arxiv.org/abs/2608.14706 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc680b4bc069 (Metraipolis archive dc_dc680b4bc069, sha256 8d856af99e347668d71a947278cbc45cbfc1c1b148e39343cef3edf2817a4afc)

BibTeX

@misc{dcdc680b4bc069,
  title = {Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning — arXiv:2608.14706},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14706},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc680b4bc069; sha256 8d856af99e347668d71a947278cbc45cbfc1c1b148e39343cef3edf2817a4afc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14706. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data. We introduce Equilibrium Forcing (EqF), a simplified framework for video denoising generative models without noise level conditioning. EqF pioneers modular training- and inference-time designs for noise-unconditional generation that decouple learning the denoising field from sampling. This flexibility allows for inference-time algorithms that operate in a closed loop by adapting to feedback from the sample, improving video quality and consistency on challenging autoregressive video generation benchmarks. Extensive analysis elucidates exactly how removing the noise level conditioning enables EqF's data-dependent inference properties to surpass the performance of standard noise level-conditional denoising video methods.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14706 — 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 2026-10-18T16:29:13.944Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).