ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing
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, we propose \textbf{ElasticTTT}, a novel framework that pr
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%DiffusionGemma: 4x faster text generation →
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzySimilar title/name (fuzzy) · 59%Developer-Y/cs-video-courses →
“Fuzzy title match (0.73): “ElasticTTT: Prior-Preserving Test-Time Tuning for Video Edit” ≈ “Developer-Y/cs-video-courses””
- LinkedLinked via arxiv author · 85%Yueyi Liu →
“ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing”
- LinkedLinked via arxiv author · 85%Chi Zhang →
“ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing”
- LinkedLinked via arxiv author · 85%Sen Cui →
“ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing”
- LinkedLinked via arxiv author · 85%Miao Liu →
“ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing”