Metraipolis › archive › dc_27aef2b414f6
On the Resilience of Text-to-Video Diffusion Models to Hardware Faults — arXiv:2608.29598
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29598
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:36:50.848Z
- SHA-256 of the archived text
7bec3fd05197b472fbfcdbe55c72a0e95b7051265ae4fec92bd37a2065a48315- Stable URL of this page
https://metraipolis.com/documento/dc_27aef2b414f6
How to cite
On the Resilience of Text-to-Video Diffusion Models to Hardware Faults — arXiv:2608.29598 — arXiv (en), https://arxiv.org/abs/2608.29598 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27aef2b414f6 (Metraipolis archive dc_27aef2b414f6, sha256 7bec3fd05197b472fbfcdbe55c72a0e95b7051265ae4fec92bd37a2065a48315)
BibTeX
@misc{dc27aef2b414f6,
title = {On the Resilience of Text-to-Video Diffusion Models to Hardware Faults — arXiv:2608.29598},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29598},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27aef2b414f6; sha256 7bec3fd05197b472fbfcdbe55c72a0e95b7051265ae4fec92bd37a2065a48315},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29598. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present the first systematic study of the resilience of text-to-video (T2V) diffusion models under random hardware-level faults. While T2V models are widely used for automated video generation due to their ability to produce high-quality, temporally coherent, and realistic videos, their iterative denoising process and spatiotemporal dependencies introduce unique failure modes. We perform an extensive fault-injection study covering both computational and memory faults across three T2V models and a representative benchmark. Our results show that (1) a single fault can degrade overall performance by up to 3.7\%, with semantic correctness more affected than perceptual quality; (2) memory faults are more damaging than computational faults, high-order exponent bits are particularly vulnerable, and the widely-used bfloat16 is more susceptible than alternative formats; and (3) 7-28\% of faults cause visible artifacts, including semantic changes such as added objects, suggesting that single faults are sufficient to alter output semantics. Our findings reveal reliability risks in deployed T2V systems and motivate further research on improving fault resilience. Code: \href{ this https URL }{ this https URL }.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.29598 — 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 2026-10-17T08:13:26.756Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).