AI Paper Atlas

Research map / Video / Video generation

LoL: Longer than Longer, Scaling Video Generation to Hour

Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh

CVPR 2026 · Video › Video generation · approach: Autoregressive long video generation · 32 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 multi-head RoPE jitter (LoL) to position extrapolationLongLive · VBench 100s videos (128 MovieGen prompts)Sink-Collapse Max: 73.06 -> 16.67Improved
add multi-head RoPE jitter (LoL) to position extrapolationLongLive · VBench 100s videos (128 MovieGen prompts)Sink-Collapse Avg: 30.54 -> 3.93Improved
add multi-head RoPE jitter (LoL) to position extrapolationSelf-Forcing++ · VBench 100s videos (128 MovieGen prompts)Sink-Collapse Max: 68.07 -> 22.70Improved
add multi-head RoPE jitter (LoL) to position extrapolationLongLive · VBench 100s videos (128 MovieGen prompts)Dynamic Degree: 34.62 -> 35.27No clear effect
add multi-head RoPE jitter (LoL) to position extrapolationSelf-Forcing++ · VBench 100s videos (128 MovieGen prompts)Dynamic Degree: 83.32 -> 81.20No clear effect
use position interpolation instead of extrapolationLongLive · VBench 100s videos (128 MovieGen prompts)Dynamic Degree: 34.62 -> 00.35Hurt
use YARN instead of extrapolationLongLive · VBench 100s videos (128 MovieGen prompts)Dynamic Degree: 34.62 -> 2.67Hurt
use NTK instead of extrapolationLongLive · VBench 100s videos (128 MovieGen prompts)Sink-Collapse Max: 73.06 -> 41.11Mixed
use RIFLEx single-dimension frequency change instead of extrapolation (ablation)LongLive · VBench 100s videos (128 MovieGen prompts)Sink-Collapse Max: 73.06 -> 70.95No clear effect
vary RoPE base theta from 6000 to 20000 (ablation)LongLive · RoPE base sweepsink-collapse positionNo clear effect
alter frequency of any single RoPE dimension (ablation)LongLive · RoPE dimension sweepsink-collapseNo clear effect
increase jitter intensity sigma from 0.1 to 0.8 (ablation)LongLive · Jitter intensity sweepsink-collapse: 0.1 -> 0.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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