AI Paper Atlas

Research map / Video / Video generation

Helios: Real Real-Time Long Video Generation Model

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

TPAMI 2026 · Video › Video generation · approach: Autoregressive long video generation · 77 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Guidance Attention (ablation)Helios-Base · Long video ablation (Total)Total score: 6.23 -> 6.47Improved
add causal mask on self-attention in Guidance Attention (ablation)Helios-Base · Long video ablation (Total)Total score: unstable training processHurt
add First Frame Anchor (ablation)Helios-Base · Long video ablation (Total)Total score: 5.51 -> 6.47Improved
add Frame-Aware Corrupt (ablation)Helios-Base · Long video ablation (Total)Total score: 4.70 -> 6.47Improved
add Coarse-to-Fine Learning (ablation)Helios-Distilled · Long video ablation (Total)Total score: 5.31 -> 6.34Improved
add Adversarial Post-Training (ablation)Helios-Distilled · Long video ablation (Total)Total score: 6.31 -> 6.34Improved
replace Self-Forcing distillation with Helios distillation (ablation)Helios-Distilled · Long video ablation (Total)Total score: 6.11 -> 6.34Improved
use unidirectional rather than bidirectional teacher (ablation)Helios-Distilled · Long video ablation (Total)Total score: 4.75 -> 6.34Improved
replace DMD with Decouple DMD (ablation)Helios-Distilled · Long video ablation (Total)Total score: 6.34 -> 5.21Hurt
add reward-weighted regression post-training (ablation)Helios-Distilled · Long video ablation (Total)Total score: 6.34 -> 6.23Hurt
add Flash Normalization and Flash RoPE (ablation)Wan-2.1-T2V-14B · DiT inference timeseconds: 98.68 -> 84.41Improved
distill Helios-Base into Helios-DistilledHelios-Base · 120-1440-frame long video (Total)Total score: 6.57 -> 6.94Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy