AI Paper Atlas

Research map / Video / Video generation

MotionStream: Real-Time Video Generation with Interactive Motion Controls

Joonghyuk Shin, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Jaesik Park, Eli Shechtman, Xun Huang

ICLR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 72 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
distill bidirectional teacher into causal studentWan 2.1-1.3B teacher · DAVIS validation (FPS vs EPE)FPS: 0.79 -> 16.7Improved
distill bidirectional teacher into causal studentWan 2.1-1.3B teacher · DAVIS validationEPE: 5.35 -> 7.80Hurt
use sinusoidal PE with track head instead of RGB-VAE track encoding (ablation)track representation · DAVISEPE: 8.57 -> 6.54Improved
add attention sink (c3s1w1 vs c3s0w1) (ablation)MotionStream causal student · Sora ExtendedLPIPS: 0.501 -> 0.464Improved
add attention sink (c3s1w1 vs c3s0w1) (ablation)MotionStream causal student · Sora ExtendedEPE: 26.64 -> 25.34Improved
increase chunk size from 1 to 3 (ablation)MotionStream causal student · Sora ExtendedEPE: 76.21 -> 25.34Improved
increase chunk size from 1 to 3 (ablation)MotionStream causal student · Sora Extendedthroughput (FPS): 13.26 -> 16.92Improved
use sink plus single-chunk window instead of Self Forcing sliding window (ablation)MotionStream causal student · Sora ExtendedLPIPS: 0.480 -> 0.464Improved
enlarge local attention window beyond one chunk (ablation)MotionStream causal student · Sora extrapolationqualityHurt
add more than one sink chunk (ablation)MotionStream causal student · Sora extrapolationqualityNo clear effect
swap full VAE for Tiny VAE decoder (ablation)MotionStream Wan 2.1-1.3B · Sora demo subsetthroughput (FPS): 16.7 -> 29.5Improved
swap full VAE for Tiny VAE decoder (ablation)MotionStream Wan 2.1-1.3B · Sora demo subsetLPIPS: 0.360 -> 0.365No clear effect

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