AI Paper Atlas

Research map / Video / Video generation

OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

Zhaochong An, Menglin Jia, Haonan Qiu, Zijian Zhou, Xiaoke Huang, Zhiheng Liu, Weiming Ren, Kumara Kahatapitiya, Ding Liu, Sen He, Chenyang Zhang, Tao Xiang and 3 more

CVPR 2026 · Video › Video generation · approach: Autoregressive long video generation · 25 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 both Adaptive Conditioner and Frame Selection to last-frame-only conditioning (ablation)OneStory (Wan2.1 I2V) · Text-to-multi-shot ablationCharacter consistency: 0.5153 -> 0.5874Improved
add both Adaptive Conditioner and Frame Selection to last-frame-only conditioning (ablation)OneStory (Wan2.1 I2V) · Text-to-multi-shot ablationSemantic alignment: 0.1814 -> 0.2389Improved
add shot inflation (inflate two-shot clips to three shots) (ablation)OneStory training · Text-to-multi-shot ablationCharacter consistency: 0.5514 -> 0.5649Improved
add decoupled conditioning curriculum on top of shot inflation (ablation)OneStory training · Text-to-multi-shot ablationCharacter consistency: 0.5649 -> 0.5874Improved
add decoupled conditioning curriculum on top of shot inflation (ablation)OneStory training · Text-to-multi-shot ablationEnvironment consistency: 0.5790 -> 0.5752Hurt
increase context tokens from one to three latent-frame equivalents (ablation)OneStory Adaptive Conditioner · Text-to-multi-shot ablationEnvironment consistency: 0.5752 -> 0.5863Improved
increase context tokens from one to three latent-frame equivalents (ablation)OneStory Adaptive Conditioner · Text-to-multi-shot ablationCharacter consistency: 0.5874 -> 0.5926Improved
use automatic frame selection instead of uniform or most-recent sampling (ablation)OneStory · Qualitative frame selection comparisoncontextual consistencyImproved
use OneStory instead of fixed-window Mask2DiTmulti-shot generation · Text-to-multi-shotCharacter consistency: 0.5472 -> 0.5874Improved
use OneStory instead of keyframe conditioning (StoryDiffusion + Wan2.1)multi-shot generation · Text-to-multi-shotSemantic alignment: 0.2217 -> 0.2389Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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