Cite
Notes
Only stored in your browser.
Attribution
InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion
arXiv 2025
ACG: Action Coherence Guidance for Flow-based VLA models
Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models
from 3 papers
Jaegul Choo
Kinam Kim
Hoiyeong Jin
Junha Hyung
Minho Park
DongJin Kim
Hojoon Lee
Huijin Choi
Hyeonji Kim
Jeongho Kim