AI Paper Atlas

Research map / Video / Video generation

Long Context Tuning for Video Generation

Yuwei Guo, Ceyuan Yang, Ziyan Yang, Zhibei Ma, Zhijie Lin, Zhenheng Yang, Dahua Lin, Lu Jiang

ICCV 2025 · Video › Video generation · approach: Autoregressive long video generation · 87 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 Long Context Tuning (ablation)pre-trained single-shot 3B model · VBench single-shotAesthetic: 52.09 -> 55.91Improved
add Long Context Tuning (ablation)pre-trained single-shot 3B model · VBench single-shotQuality: 63.37 -> 64.23Improved
add Long Context Tuning (ablation)pre-trained single-shot 3B model · VBench single-shotText alignment: 30.81 -> 32.22Improved
add Long Context Tuning (ablation)pre-trained single-shot 3B model · VBench single-shotConsistency: 94.98 -> 95.06No clear effect
use auto-regressive instead of joint generation (bidirectional) (ablation)LCT bidirectional · multi-shot VBenchText alignment: 29.33 -> 30.24Improved
use auto-regressive instead of joint generation (bidirectional) (ablation)LCT bidirectional · multi-shot VBenchQuality: 57.68 -> 56.62Hurt
use context-causal attention instead of bidirectional (auto-regressive) (ablation)LCT · multi-shot VBenchQuality: 56.62 -> 50.31Hurt
use context-causal attention instead of bidirectional (auto-regressive) (ablation)LCT · multi-shotfidelity to historyImproved
raise history conditioning noise timestep (ablation)LCT auto-regressive · multi-shoterror accumulation vs history fidelityMixed
add 1K steps of context-causal fine-tuning from bidirectional weights (ablation)LCT context-causal · multi-shotidentity consistencyImproved
use LCT instead of VideoStudioVideoStudio · scene-levelText alignment: 28.00 -> 30.14Improved
use LCT instead of VideoStudioVideoStudio · scene-levelUser study: 2.14 -> 3.79Improved

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