Signals 4 · free daily AI digest

FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching

Paper recorded by Signals 4 on 2026-09-28 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29

Category: cs.CV · 计算机视觉 · first seen 2026-09-29

Abstract

Tool-based image editing (image retouching) is commonly formulated with autoregressive multimodal large language models (MLLMs) that sequentially generate reasoning, tool selections, and parameter values. In this work, we present a novel approach to tool-based image editing by framing the task as a flow matching problem. We introduce FlowTool, a framework that directly models the distribution of h

Read on arXiv →

#11 most recent of 342 cs.CV papers we have recorded · ↑ newer: DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Tes · ↓ older: Many Eyes, One World: Feed-Forward 3D Reconstruction from Mixed Camera
Cite this page: FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching: the #11 most recent of 342 cs.CV papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/flowtool-controlling-tool-parameter-in-image-retouching-via-flow-matching.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