EUVIMEDEUVIMED entdecken
Crossref

Helios: Real Real-Time Long Video Generation Model

Shenghai Yuan, Yuanyang Yin, Zongjian Li, Xinwei Huang, Xiao Yang, Li Yuan

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-12

DOI: 10.1109/tpami.2026.3750238 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Shenghai Yuan und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce Helios, the first 14B video generation model that runs at 19.5 FPS on a single NVIDIA H100 GPU and supports minute-scale generation while matching the quality of a strong baseline. We make breakthroughs along three key dimensions: (1) robustness to long-video drifting without commonly used anti-drifting heuristics such as self-forcing, errorbanks, or keyframe sampling; (2) real-time generation without standard acceleration techniques such as KV-cache, sparse/linear attention, or quantization; and (3) training without parallelism or sharding frameworks, enabling image-diffusion-scale batch sizes while fitting up to four 14B models within 80 GB of GPU memory. Specifically, Helios is a 14B autoregressive diffusion model with a unified input representation that natively supports T2V, I2V, and V2V tasks. To mitigate drifting in long-video generation, we characterize typical failure modes and propose simple yet effective training strategies that explicitly simulate drifting during training, while eliminating repetitive motion at its source. For efficiency, we heavily compress the historical and noisy context and reduce the number of sampling steps, yielding computational costs comparable to or even lower than those of 1.3B video generative models. Moreover, we introduce infrastructure-level optimizations that accelerate both inference and training while reducing memory consumption. Extensive experiments demonstrate that Helios consistently outperforms prior methods on both short- and long-video generation. We release the training and inference code and model checkpoints to support further development by the community.

Zitieren

APA

Yuan, S., Yin, Y., Li, Z., Huang, X., Yang, X., & Yuan, L. (2026). Helios: Real Real-Time Long Video Generation Model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-12. https://doi.org/10.1109/tpami.2026.3750238

Vancouver

Yuan S, Yin Y, Li Z, Huang X, Yang X, Yuan L. Helios: Real Real-Time Long Video Generation Model. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-12. doi:10.1109/tpami.2026.3750238

BibTeX
@article{Yuan2026,
  author = {Yuan, Shenghai and Yin, Yuanyang and Li, Zongjian and Huang, Xinwei and Yang, Xiao and Yuan, Li},
  title = {Helios: Real Real-Time Long Video Generation Model},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  pages = {1--12},
  doi = {10.1109/tpami.2026.3750238}
}
Kostenlos starten →