AI Paper Atlas

Research map / Video / Video generation

Improving Autoregressive Video Modeling with History Understanding

Wenyang Luo, Haina Qin, Bing Li, Jiwen Lu, Xin Tao, Pengfei Wan, Kun Gai

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
add masked history modeling (MiMo) to the ACDiT baseline (ablation)ACDiT-B · Kinetics-600 (DiT-B, 100K steps)FVD: 54.814 -> 36.601Improved
add MiMo on top of REPA-Both (ablation)REPA-Both · Kinetics-600 (DiT-B)FVD: 36.542 -> 34.133Improved
add REPA feature distillation on history frames onlyACDiT-B · Kinetics-600 (DiT-B)FVD: 54.814 -> 40.022Improved
add REPA on both history and future frames instead of future onlyACDiT-B + REPA · Kinetics-600 (DiT-B)FVD: 40.253 -> 36.542Improved
use history+future REPA instead of only future frames (accuracy)ACDiT-B + REPA · Kinetics-600 linear probingaccuracy: 17.04 -> 19.23Improved
predict next frame in addition to current frame as masked-history target (ablation)MiMo · Kinetics-600 (DiT-B)FVD: 41.832 -> 36.601Improved
predict current frame in addition to next frame as masked-history target (ablation)MiMo · Kinetics-600 (DiT-B)FVD: 37.782 -> 36.601Improved
add NextNext frame target (ablation)MiMo · Kinetics-600 (DiT-B)FVD: 36.601 -> 36.263No clear effect
place decoder after layer 11 instead of 12 (ablation)MiMo · Kinetics-600 (DiT-B)FVD: 36.601 -> 35.815No clear effect
place decoder after layer 9 instead of 12 (ablation)MiMo · Kinetics-600 (DiT-B)FVD: 36.601 -> 37.593Hurt
add RoPE and separate LayerNorm for history frames (ablation)Vanilla DiT · Kinetics-600 (DiT-B)FVD: 37.763 -> 36.601Improved
set lambda to 0.5 instead of 0.1 (ablation)MiMo · Kinetics-600 (DiT-B)FVD: 40.213 -> 36.601Improved

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