Signals 4 · free daily AI digest

Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network

Paper recorded by Signals 4 on 2026-09-17 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.CV · 计算机视觉 · first seen 2026-09-18

Abstract

Text-guided image editing must introduce the requested changes while preserving unrelated source content. Diffusion-based editors rely on spatial controls whose inaccuracies can leave edits incomplete or alter unrelated regions. Causal autoregressive editors face a further constraint: their fixed decoding order limits revision of earlier decisions. We introduce RefineEdit, a training-free prompt-t

Read on arXiv →

#11 most recent of 237 cs.CV papers we have recorded · ↑ newer: PROVIA: Procedure State Tracking for Online Mistake Detection in Egoce · ↓ older: PhGS: Post-Hoc Pruning and Refinement of Single-View Feed-Forward 3D G
Cite this page: Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network: the #11 most recent of 237 cs.CV papers we have recorded (as of 2026-09-17). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/refinement-is-inherently-editable-training-free-prompt-to-prompt-image-editing-w.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions