AI Paper Atlas

Research map / Video / Video generation

QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers

Kyobin Choo, Youngmin Kim, Hyunkyung Han, Geunrip Park, Chanyoung Kim, Sunyoung Jung, Seong Jae Hwang

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 0 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 STCD semantic channel selection (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.297 -> 0.237Improved
add STCD semantic channel selection (ablation)Qwerty on CogVideoX · VIPSeg object controlFTD: 0.542 -> 0.473Improved
warp queries only instead of keys only (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.293 -> 0.237Improved
warp queries only instead of queries and keys (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.290 -> 0.237Improved
warp queries instead of attention output (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.288 -> 0.237Improved
also warp temporal RoPE (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.237 -> 0.285Hurt
add spatial RoPE warping (ablation)Qwerty on CogVideoX · VIPSeg object controlFVD (x10^3): 1.578 -> 0.668Improved
add self-guided latent optimization to query-warped denoising (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.274 -> 0.237Improved
add self-guided latent optimization to query-warped denoising (ablation)Qwerty on CogVideoX · VIPSeg object controlFTD: 0.501 -> 0.473Improved
add query-warped denoising to latent optimization (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.355 -> 0.237Improved
add phase-consistency loss (ablation)Qwerty on Wan · DL3DV camera controlFTD: 0.285 -> 0.237Improved
apply query warping to Wan without latent optimizationWan 2.2 TI2V-5B · DL3DV camera controlFTD: 0.367 -> 0.274Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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