paper-with-me

Papers

VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model

2026-03-09 · Jinxiang Lai, Wenzhe Zhao, Zexin Lu, Hualei Zhang, Qinyu Yang, Rongwei Quan, Zhimin Li, Shuai Shao, Song Guo, Qinglin Lu arxiv

Visual content generation has advanced from single-image to multi-image workflows, yet existing agents remain largely plan-driven and lack systematic reflection mechanisms to correct mid-trajectory visual errors. To address this limitation, we propose VisionCreator-R1, a native visual generation agent with explicit reflection, together with a Reflection-Plan Co-Optimization (RPCO) training methodology. Through extensive experiments and trajectory-level analysis, we uncover reflection-plan optimization asymmetry in reinforcement learning (RL): planning can be reliably optimized via plan rewards, while reflection learning is hindered by noisy credit assignment. Guided by this insight, our RPCO first trains on the self-constructed VCR-SFT dataset with reflection-strong single-image trajectories and planning-strong multi-image trajectories, then co-optimization on VCR-RL dataset via RL. This yields our unified VisionCreator-R1 agent, which consistently outperforms Gemini2.5Pro on existing benchmarks and our VCR-bench covering single-image and multi-image tasks.

📄 PDF Abstract BibTeX arXiv:2603.08812

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation

2026-03-03 · Jinxiang Lai, Zexin Lu, Jiajun He, Rongwei Quan 외 arxiv

Visual content creation tasks demand a nuanced understanding of design conventions and creative workflows-capabilities challenging for general models, while workflow-based agents lack specialized knowledge for autonomous…

Reinforcement Learning

PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal

2024-02-04 · Tao Wang, Wanglong Lu, Kaihao Zhang, Wenhan Luo 외

Existing single image reflection removal (SIRR) methods using deep learning tend to miss key low-frequency (LF) and high-frequency (HF) differences in images, affecting their effectiveness in removing reflections. To add…

Reflection Removal

EmCom-Diffusion: Probing Visual Reflection in Emergent Languages via Image Generation

2026-07-04 · Haruumi Omoto, Tadahiro Taniguchi arxiv

Measuring the extent to which emergent languages encode the visual content of their inputs is an open problem. We refer to this property as visual reflection: the extent to which emergent messages preserve information ab…

Image Generation

Reflection Generation for Composite Image Using Diffusion Model

2026-04-02 · Haonan Zhao, Qingyang Liu, Jiaxuan Chen, Li Niu arxiv

Image composition involves inserting a foreground object into the background while synthesizing environment-consistent effects such as shadows and reflections. Although shadow generation has been extensively studied, ref…

ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation

2024-05-27 · Houxing Ren, Mingjie Zhan, Zhongyuan Wu, Aojun Zhou 외

Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating fe…

Code GenerationHumanEvalMathematical Reasoningmbpp