From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing
Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for instruction adherence and visual quality. The orchestrator is trained to maximize these rewards, and successful trajectories are used to refine the planner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Image EditingSimilar Papers 제목 키워드 기반
SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments
Recent works have explored integrating Vision-Language Models (VLMs) with classical planners that rely on symbolic representations of planning problems to generate long-horizon plans for complex embodied tasks. However, …
Learning to Plan and Realize Separately for Open-Ended Dialogue Systems
Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically cons…
Text GenerationCoPAL: Corrective Planning of Robot Actions with Large Language Models
In the pursuit of fully autonomous robotic systems capable of taking over tasks traditionally performed by humans, the complexity of open-world environments poses a considerable challenge. Addressing this imperative, thi…
Motion GenerationMotion PlanningTask and Motion PlanningAlpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
Alpa automates model-parallel training of large deep learning (DL) models by generating execution plans that unify data, operator, and pipeline parallelism. Existing model-parallel training systems either require users t…
SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science
Large Language Models (LLMs) have revolutionized automated data analytics and machine learning by enabling dynamic reasoning and adaptability. While recent approaches have advanced multi-stage pipelines through multi-age…
Feature Engineering