A training-free, two-stage erasure method (prompt embedding adjustment plus adversarial noise guidance) is claimed to cut unwanted text-to-video output by 46%, but the submitted full text is an unrelated quantum-coding paper.
Title resolution pending
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
-
VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
A training-free, two-stage erasure method (prompt embedding adjustment plus adversarial noise guidance) is claimed to cut unwanted text-to-video output by 46%, but the submitted full text is an unrelated quantum-coding paper.