AI Paper Atlas

Research map / Video / Video generation

Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion

yang yang, Tianyi Zhang, Wei Huang, Jinwei Chen, Boxi Wu, Xiaofei He, Deng Cai, Bo Li, Peng-Tao Jiang

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 16 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 tri-region RoPE (ablation)LongLive baseline · 60s interactive ablationdynamic degree: 26.37 -> 74.83Improved
add tri-region RoPE (ablation)LongLive baseline · 60s interactive ablationquality score: 78.92 -> 81.72Improved
add tri-region RoPE (ablation)LongLive baseline · 60s interactive ablationCLIP score: 23.58 -> 23.71Improved
add anchor-guided re-cache on top of tri-region RoPE (ablation)Anchor Forcing · 60s interactive ablationquality score: 81.72 -> 82.25Improved
add anchor-guided re-cache on top of tri-region RoPE (ablation)Anchor Forcing · 60s interactive ablationCLIP score: 23.71 -> 23.85Improved
add anchor-guided re-cache on top of tri-region RoPE (ablation)Anchor Forcing · 60s interactive ablationdynamic degree: 74.83 -> 73.00Hurt
use anchor-guided re-cache instead of KV re-cache (ablation)LongLive baseline · 60s interactive ablationdynamic degree: 26.37 -> 50.73Improved
use Flush re-cache instead of KV re-cache (ablation)LongLive baseline · 60s interactive ablationdynamic degree: 26.37 -> 27.60No clear effect
use bounded RoPE instead of unbounded RoPE (ablation)LongLive baseline · 60s interactive ablationdynamic degree: 26.37 -> 29.09No clear effect
use tri-region RoPE instead of bounded RoPE (ablation)LongLive baseline · 60s interactive ablationdynamic degree: 29.09 -> 74.83Improved
use Anchor Forcing instead of LongLive on 30s generationLongLive · VBenchLong 30s single-promptdynamic score: 40.19 -> 79.17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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