VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
Roformer: Enhanced transformer with 9 rotary position embedding.Neurocomputing, 568:127063,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VideoCoF: Unified Video Editing with Temporal Reasoner
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.