AI Paper Atlas

Research map / Video / Video generation

Real-Time Motion-Controllable Autoregressive Video Diffusion

Kesen Zhao, Jiaxin Shi, Beier Zhu, Junbao Zhou, Xiaolong Shen, Yuan Zhou, Qianru Sun, Hanwang Zhang

ICLR 2026 · Video › Video generation · approach: Efficient video diffusion models

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 RL post-training (GRPO with trajectory reward) (ablation)AR-Drag · Motion-control benchmark (206 clips)FVD: 210.35 -> 187.49Improved
add RL post-training (ablation)AR-Drag · Motion-control benchmark (206 clips)motion consistency: 4.12 -> 4.37Improved
add Self-Rollout training (ablation)AR-Drag · Motion-control benchmark (206 clips)FVD: 353.75 -> 187.49Improved
add Self-Rollout training (ablation)AR-Drag · Motion-control benchmark (206 clips)FID: 38.13 -> 28.98Improved
fine-tune motion control and distill to few-step AR model (ablation)Wan2.1-1.3B-I2V · Motion-control benchmark (206 clips)latency (s): 45.72 -> 0.44Improved
use chunk size 3 instead of frame-wise (chunk 1) (ablation)AR-Drag · Motion-control benchmark (206 clips)FID: 28.98 -> 27.47No clear effect
enlarge KV cache from 7 to 15 or 25 frames (ablation)AR-Drag · Motion-control benchmark (206 clips)FID: 28.98 -> 28.96 (15), 28.99 (25)No clear effect
use AR-Drag instead of bidirectional multi-step teacherAR-Drag · Motion-control benchmark (206 clips)FVD: 151.46 -> 187.49Hurt
use Self-Rollout full step-by-step rollout instead of Self-Forcing collapsed KV updateAR-Drag vs Self-Forcing · Motion-control benchmark (206 clips)FID: 34.47 -> 28.98Improved

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