ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing
Quick summary
arXiv:2607.21529v2 Announce Type: replace-cross Abstract: Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, there exists a foundational mismatch between the distribution-mapping nature of generative models and the single-point optimization of standard TTT. In this paper, we demonstrate that this mismatch triggers \textit{Prior Collapse}, a degenerate state where the model discards the text conditions and spatial latents, collapsing generations to the source video, or entangling the features of distinct regions. To resolve this,
Key takeaways
- arXiv:2607.21529v2 Announce Type: replace-cross Abstract: Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing.
- However, there exists a foundational mismatch between the distribution-mapping nature of generative models and the single-point optimization of standard TTT.
- In this paper, we demonstrate that this mismatch triggers \textit{Prior Collapse}, a degenerate state where the model discards the text conditions and spatial latents, collapsing generations to the source video, or entangling the features of distinct regions.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments