collaborators

1 paper

cs.CV2025

MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing

Shreya Kadambi, Risheek Garrepalli, Shubhankar Borse +2

Despite the remarkable success of diffusion models in text-to-image generation, their effectiveness in grounded visual editing and compositional control remains challenging. Motiva…