AI Paper Atlas

Research map / Video / Video generation

Tea-Adapter: Teacher Adapter for Efficient Conditional Generation

Yinhan Zhang, Yue Ma, Fangqiu Yi, Chenyang Qi, Chi Zhang, Kunyu Feng, Zeyu Wang

CVPR 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 Mixture of Condition Experts layer (ablation)Tea-Adapter · Depth map control (Table 2)FVD: 303.202 -> 292.341Improved
add Mixture of Condition Experts layer (ablation)Tea-Adapter · Depth map control (Table 2)LPIPS: 0.268 -> 0.251Improved
keep all adapters instead of using half of them (ablation)Tea-Adapter · Depth map control (Table 2)FVD: 398.013 -> 292.341Improved
reduce adapters from 12 to 7 (ablation)Tea-Adapter · Adapter scalingCondition fidelityNo clear effect
transfer control from a small teacher to the 14B student via adapters instead of DiT-ControlNet on CannyWan2.1-14B · Canny edge controlFVD: 425.249 -> 289.565Improved
use Tea-Adapter instead of full fine-tuning of Wan2.1-14BWan2.1-14B · Canny edge controlFVD: 229.186 -> 289.565Hurt
use Tea-Adapter instead of Ctrl-Adapter on depthvideo DiT · Depth map controlFVD: 448.291 -> 292.341Improved
use Tea-Adapter instead of Ctrl-Adapter for temporal consistencyvideo DiT · Video generationTemporal consistency: 0.981 -> 0.984Improved

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