AI Paper Atlas

Research map / Video / Video generation

Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation

Shihan Cheng, Nilesh Kulkarni, David Hyde, Dmitriy Smirnov

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 1 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
train on simple synthetic scene instead of photorealistic scene (ablation)Wan2.1 fine-tuning (shutter speed) · One-shot data comparisonX-CLIP score: 23.278 -> 24.777Improved
train on simple synthetic scene instead of photorealistic scene (ablation)Wan2.1 fine-tuning (aperture) · One-shot data comparisonX-CLIP score: 19.824 -> 25.105Improved
train on simple synthetic scene instead of photorealistic scene (ablation)Wan2.1 fine-tuning (color temperature) · One-shot data comparisonX-CLIP score: 24.456 -> 25.015Improved
train on simple synthetic scene instead of photorealistic scene (ablation)Wan2.1 fine-tuning (aperture) · One-shot data comparisonVQA score: 0.021 -> 0.343Improved
train on simple synthetic scene instead of photorealistic scene (ablation)Wan2.1 fine-tuning (shutter speed) · One-shot data comparisonVQA score: 0.096 -> 0.352Improved
train on simple synthetic scene instead of photorealistic scene (ablation)Wan2.1 fine-tuning · One-shot data comparison, FEP driftSSF / SS-FD drift rateImproved
discard backbone LoRA from shallow two-thirds of blocks at inference (decoupled) (ablation)Wan2.1 + adapter (aperture) · SVP 96-prompt suiteVQA score: 0.427 -> 0.513Improved
decoupled instead of full-LoRA inference (ablation)Wan2.1 + adapter (shutter speed) · SVP 96-prompt suiteVQA score: 0.453 -> 0.521Improved
decoupled instead of full-LoRA inference (ablation)Wan2.1 + adapter (color temperature) · SVP 96-prompt suiteVQA score: 0.550 -> 0.532Hurt
decoupled instead of full-LoRA inference (ablation)Wan2.1 + adapter (shutter speed) · SVP 96-prompt suiteDynamic degree: 0.688 -> 0.469Improved
decoupled instead of full-LoRA inference (ablation)Wan2.1 + adapter · SVP 96-prompt suiteX-CLIP score: 25.295 -> 25.587 (shutter)Mixed
joint training of backbone LoRA with conditional adapter instead of adapter-only (ablation)Wan2.1 adapter · Block 27 singular value spectrumeffective rank of y_cond: high-rank -> effective rank of 1Improved

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