paper-with-me

Papers

SIDiffAgent: Self-Improving Diffusion Agent

2026-02-02 · Shivank Garg, Ayush Singh, Gaurav Kumar Nayak arxiv

Text-to-image diffusion models have revolutionized generative AI, enabling high-quality and photorealistic image synthesis. However, their practical deployment remains hindered by several limitations: sensitivity to prompt phrasing, ambiguity in semantic interpretation (e.g., ``mouse" as animal vs. a computer peripheral), artifacts such as distorted anatomy, and the need for carefully engineered input prompts. Existing methods often require additional training and offer limited controllability, restricting their adaptability in real-world applications. We introduce Self-Improving Diffusion Agent (SIDiffAgent), a training-free agentic framework that leverages the Qwen family of models (Qwen-VL, Qwen-Image, Qwen-Edit, Qwen-Embedding) to address these challenges. SIDiffAgent autonomously manages prompt engineering, detects and corrects poor generations, and performs fine-grained artifact removal, yielding more reliable and consistent outputs. It further incorporates iterative self-improvement by storing a memory of previous experiences in a database. This database of past experiences is then used to inject prompt-based guidance at each stage of the agentic pipeline. \modelour achieved an average VQA score of 0.884 on GenAIBench, significantly outperforming open-source, proprietary models and agentic methods. We will publicly release our code upon acceptance.

📄 PDF Abstract BibTeX arXiv:2602.02051

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Diffusion Self-Weighted Guidance for Offline Reinforcement Learning

2025-05-23 · Augusto Tagle, Javier Ruiz-del-Solar, Felipe Tobar

Offline reinforcement learning (RL) recovers the optimal policy $\pi$ given historical observations of an agent. In practice, $\pi$ is modeled as a weighted version of the agent's behavior policy $\mu$, using a weight fu…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

SceneDM: Scene-level Multi-agent Trajectory Generation with Consistent Diffusion Models

2023-11-27 · Zhiming Guo, Xing Gao, Jianlan Zhou, Xinyu Cai 외

Realistic scene-level multi-agent motion simulations are crucial for developing and evaluating self-driving algorithms. However, most existing works focus on generating trajectories for a certain single agent type, and t…

Generating Driving Scenes with Diffusion

2023-05-29 · Ethan Pronovost, Kai Wang, Nick Roy

In this paper we describe a learned method of traffic scene generation designed to simulate the output of the perception system of a self-driving car. In our "Scene Diffusion" system, inspired by latent diffusion, we use…

object-detectionObject DetectionScene Generation

JEDI: Latent End-to-end Diffusion Mitigates Agent-Human Performance Asymmetry in Model-Based Reinforcement Learning

2025-05-26 · Jing Yu Lim, Zarif Ikram, Samson Yu, Haozhe Ma 외

Recent advances in model-based reinforcement learning (MBRL) have achieved super-human level performance on the Atari100k benchmark, driven by reinforcement learning agents trained on powerful diffusion world models. How…

Model-based Reinforcement Learning

Diffusion Adaptation over Networks

2012-05-18 · Ali H. Sayed

Adaptive networks are well-suited to perform decentralized information processing and optimization tasks and to model various types of self-organized and complex behavior encountered in nature. Adaptive networks consist …

Distributed Optimization