Journal article · 2026 · Open access

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, PP, 1–12 · Published 1 January 2026 · DOI 10.1109/tpami.2026.3750238

Open full textCite this paper

In brief

“Helios: Real Real-Time Long Video Generation Model” is a 2026 journal article by Shenghai Yuan and 5 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 77 citations as of 16 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Pattern Analysis and Machine Intelligence.

Citations
77
Most cited in
2026 (77)
Field-weighted impact
113.50
References
91
Authors
6

Abstract

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

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, PP, 1–12. https://doi.org/10.1109/tpami.2026.3750238

MLA 9

Yuan, Shenghai, et al. “Helios: Real Real-Time Long Video Generation Model.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–12. https://doi.org/10.1109/tpami.2026.3750238.

Chicago

Yuan, Shenghai, Yuanyang Yin, Zongjian Li, Xinwei Huang, Xiao Yang, and Li Yuan. 2026. “Helios: Real Real-Time Long Video Generation Model.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–12. https://doi.org/10.1109/tpami.2026.3750238.

Harvard

Yuan, S. et al. (2026) ‘Helios: Real Real-Time Long Video Generation Model’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–12. doi:10.1109/tpami.2026.3750238.

IEEE

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

BibTeX

@article{yuan2026helios,
  title     = {{Helios: Real Real-Time Long Video Generation Model}},
  author    = {Yuan, Shenghai and Yin, Yuanyang and Li, Zongjian and Huang, Xinwei and Yang, Xiao and Yuan, Li},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2026},
  volume    = {PP},
  pages     = {1--12},
  doi       = {10.1109/tpami.2026.3750238},
  url       = {https://doi.org/10.1109/tpami.2026.3750238}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis

  • long video generation
  • real-time video generation
  • GPU memory efficiency
  • text-to-video generation
  • context compression
  • inference acceleration

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

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, PP, 1–12. https://doi.org/10.1109/tpami.2026.3750238

How many times has this paper been cited?

77 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Transactions on Pattern Analysis and Machine Intelligence: sign in and open the full text from this page.

Who wrote this paper?

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

What is the DOI of this paper?

10.1109/tpami.2026.3750238, permanently at https://doi.org/10.1109/tpami.2026.3750238. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.