AI Paper Atlas

Research map / Video / Video generation

AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction

Zhen Xing, Qi Dai, Zejia Weng, Zuxuan Wu, Yu-Gang Jiang

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 27 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 MCondition (DQFormer text condition) (ablation)AID · SSv2FVD: 152.4 -> 50.23Improved
add decomposed embedding branch (ablation)AID · SSv2FVD: 74.98 -> 50.23Improved
add multi-modal embedding branch (ablation)AID · SSv2FVD: 70.16 -> 50.23Improved
add LLaVA-predicted state prompts (ablation)AID · SSv2FVD: 64.48 -> 50.23Improved
add adapters to frozen UNet (ablation)AID · SSv2FVD: 279.42 -> 50.23Improved
add spatial adapter (ablation)AID · SSv2FVD: 68.12 -> 50.23Improved
add temporal adapters (short and long-term) (ablation)AID · SSv2FVD: 76.32 -> 50.23Improved
add short-term temporal adapter (ablation)AID · SSv2FVD: 59.62 -> 50.23Improved
add long-term temporal adapter (ablation)AID · SSv2FVD: 58.16 -> 50.23Improved
add MCondition (DQFormer text condition) (ablation)AID · SSv2KVD: 0.14 -> 0.02Improved
use AID instead of SeerSeer · BridgeFVD: 246.3 -> 21.57Improved
use AID instead of SeerSeer · SSv2FVD: 112.9 -> 50.23Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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