AI Paper Atlas

Research map / Video / Video generation

Surprise Forcing: What to Remember, When to Skip in Long Video Generation

SHUWEI SHI, Zhen Li, Muyao Niu, Chuanhao Li, Bo Zheng, Kaipeng Zhang, zheng yinqiang

ECCV 2026 · Video › Video generation · approach: Autoregressive long video generation · 6 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
use Budget-Norm gating instead of fixed threshold z=0.1 (ablation)Surprise Forcing · VBench-Long (30s prompts)Total score: 81.24 -> 83.20Improved
use Budget-Norm gating instead of fixed threshold z=2.0 (ablation)Surprise Forcing · VBench-Long (30s prompts)Total score: 81.66 -> 83.20Improved
use priority-based eviction instead of FIFO (ablation)Surprise Forcing · VBench-Long (30s prompts)Total score: 82.92 -> 83.20Improved
increase skip ratio from 0.4 to 0.6 (ablation)Surprise Forcing · VBench-Long (30s prompts)Total score: 83.20 -> 82.15Hurt
increase skip ratio from 0 to 0.4 (ablation)Surprise Forcing · VBench-Long (30s prompts)Total score: 84.03 -> 83.20Mixed
use similarity top-3 routing instead of recent-frame routing (ablation)Surprise Forcing · VBench-Long (60s MovieGen)Subject consistency: 96.25 -> 97.16Improved
use similarity top-3 routing instead of random routing (ablation)Surprise Forcing · VBench-Long (60s MovieGen)Subject consistency: 96.23 -> 97.16Improved
route 6 frames instead of 3 (ablation)Surprise Forcing · VBench-Long (60s MovieGen)Dynamic degree: 56.56 -> 54.42Hurt
increase bank size from 6 to 12 (ablation)Surprise Forcing · VBench-Long (60s MovieGen)FPS: 17.18 -> 16.70Hurt
increase target write ratio from 0.3 to 0.1 (ablation)Surprise Forcing · VBench-Long (60s MovieGen)Dynamic degree: 56.56 -> 55.16Hurt
increase target write ratio from 0.3 to 0.7 (ablation)Surprise Forcing · VBench-Long (60s MovieGen)Dynamic degree: 56.56 -> 54.74Hurt
use priority-based eviction instead of greedy least-correlation eviction (ablation)Surprise Forcing · VBench-Long (60s MovieGen)Dynamic degree: 55.00 -> 56.56Improved

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