AI Paper Atlas

Research map / Video / Video generation

Yume1.5: A Text-Controlled Interactive World Generation Model

Xiaofeng Mao, Zhen Li, Chuanhao Li, Xiaojie Xu, Kaining Ying, Kaipeng Zhang

CVPR 2026 · Video › Video generation · approach: World-model video generation · 71 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
replace TSCM with spatial compression from Yume (ablation)Yume1.5 · Yume-Benchinstruction following: 0.767 -> 0.836Improved
add TSCM instead of spatial compression (ablation)Yume1.5 · Yume-Benchmotion smoothness: 0.973 -> 0.985No clear effect
add TSCM instead of spatial compression (ablation)Yume1.5 · Yume-Benchimaging quality: 0.733 -> 0.728No clear effect
add TSCM to bound history context (ablation)Yume1.5 inference · autoregressive inference time vs video blocksinference time: constant per-step time after 8 blocks; full context 12.41s at truncationImproved
add Self-Forcing with TSCM training for few-step generation (ablation)Yume1.5 · long-video T2V, 6th segmentaesthetic quality: 0.442 -> 0.523Improved
add Self-Forcing with TSCM training for few-step generation (ablation)Yume1.5 · long-video T2V, 6th segmentimaging quality: 0.542 -> 0.601Improved
distill to 4 steps with Self-Forcing and TSCM, built on Wan2.2-5BYume1.5 · Yume-Benchgeneration time (s): 107 -> 8 (Wan-2.2-5B vs Yume1.5)Improved
switch from Yume to Yume1.5world generation · Yume-Benchaesthetic quality: 0.518 -> 0.506Hurt
switch from Yume to Yume1.5world generation · Yume-Benchimaging quality: 0.739 -> 0.728Hurt

Later papers that compared with this method

2 later accepted papers report Yume 1.5 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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