AI Paper Atlas

Research map / Video / Video generation

Mixture of Contexts for Long Video Generation

Shengqu Cai, Ceyuan Yang, Lvmin Zhang, Yuwei Guo, Junfei Xiao, Ziyan Yang, Yinghao Xu, Zhenheng Yang, Alan Yuille, Leonidas Guibas, Maneesh Agrawala, Lu Jiang and 1 more

ICLR 2026 · Video › Video generation · approach: Autoregressive long video generation

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
replace dense attention with learned top-k context routing (MoC)LCT 3B MMDiT · multi-shot 8-shot scenes (VBench)Dynamic Degree: 0.4583 -> 0.5625Improved
replace dense attention with MoC at 85% sparsityLCT 3B MMDiT · multi-shot 8-shot scenes (VBench)attention FLOPs: 1.7 x 10^13 -> 2.3 x 10^12Improved
replace dense attention with MoCLCT 3B MMDiT · multi-shot 8-shot scenes (VBench)Image Quality: 0.5140 -> 0.5003Hurt
replace dense attention with MoC3B MMDiT · single-shot 8s 320x192 (VBench)Dynamic Degree: 0.6875 -> 0.7500Improved
replace dense attention with MoC on short single-shot videos3B MMDiT · single-shot 8s 320x192 (VBench)end-to-end speedHurt
replace dense attention with MoCWan-2.1-1.3B · single-shot VBenchDynamic Degree: 0.4219 -> 0.6250Improved
add forced intra-shot links (ablation)MoC · multi-shot forced-link ablation (10k iters)Dynamic Degree: 0.0208 -> 0.5729Improved
add forced cross-modal links on top of intra-shot links (ablation)MoC · multi-shot forced-link ablation (10k iters)Image Quality: 0.4472 -> 0.5104Improved
add context drop-in and drop-out (ablation)MoC · multi-shot forced-link ablation (10k iters)Background Consistency: 0.9426 -> 0.9579Improved
reduce chunk size from 256 to 64 or 128 (ablation)MoC · single-shot ablation (30k iters)Dynamic Degree: 0.4612 -> 0.3413Hurt
increase chunk size from 256 to 1024 (ablation)MoC · single-shot ablation (30k iters)sparsity: 83% -> 35%Hurt
use top-k 1 instead of 3 (ablation)MoC · single-shot ablation (30k iters)Dynamic Degree: 0.4612 -> 0.1313Hurt

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