🛰️ Daily AI Frontier
‹ back to 2026-07-25

ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

Research Multimodal & Generative

Ranking

Overall 74
Content 75
Popularity 70

Observed public metrics from 1 member.

Merged summary

TL;DR - ElasticTTT is a test-time tuning framework for one-shot video editing that prevents pretrained diffusion models from collapsing toward the source video. It preserves the model’s generative prior while improving edit fidelity and protecting unchanged regions.

  • Identifies “Prior Collapse,” where standard single-point optimization causes lost text conditioning, source-video memorization, or entangled regional features.
  • Uses Target Distribution Regularization to discourage sharp memorization minima.
  • Introduces Contrastive CFG to steer generation away from source bias.
  • Applies an Asynchronous Noise Schedule to preserve unedited regions and reports state-of-the-art performance in extensive evaluations.

Sources (1)

ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

arXiv cs.CV Yueyi Liu, Chi Zhang, Sen Cui, Miao Liu 2026-07-23 arXiv:2607.21529
Public signals Semantic Scholar citations 1 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 1 · Influential citations 0 X · N/A Fetched 2026-08-21 14:36:29.504277 UTC

TL;DR - ElasticTTT is a test-time tuning framework for one-shot video editing that prevents pretrained diffusion models from collapsing toward the source video. It preserves the model’s generative prior while improving edit fidelity and protecting unchanged regions.

  • Identifies “Prior Collapse,” where standard single-point optimization causes lost text conditioning, source-video memorization, or entangled regional features.
  • Uses Target Distribution Regularization to discourage sharp memorization minima.
  • Introduces Contrastive CFG to steer generation away from source bias.
  • Applies an Asynchronous Noise Schedule to preserve unedited regions and reports state-of-the-art performance in extensive evaluations.
item →