Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing
Abstract
Re-Align addresses the gap between understanding and generation in in-context image generation and editing through structured reasoning-guided alignment and reinforcement learning training.
In-context image generation and editing (ICGE) enables users to specify visual concepts through interleaved image-text prompts, demanding precise understanding and faithful execution of user intent. Although recent unified multimodal models exhibit promising understanding capabilities, these strengths often fail to transfer effectively to image generation. We introduce Re-Align, a unified framework that bridges the gap between understanding and generation through structured reasoning-guided alignment. At its core lies the In-Context Chain-of-Thought (IC-CoT), a structured reasoning paradigm that decouples semantic guidance and reference association, providing clear textual target and mitigating confusion among reference images. Furthermore, Re-Align introduces an effective RL training scheme that leverages a surrogate reward to measure the alignment between structured reasoning text and the generated image, thereby improving the model's overall performance on ICGE tasks. Extensive experiments verify that Re-Align outperforms competitive methods of comparable model scale and resources on both in-context image generation and editing tasks.
Community
This paper introduces Re-Align, a unified framework for in-context image generation and editing that bridges the gap between multimodal understanding and image synthesis. Re-Align employs a structured In-Context Chain-of-Thought (IC-CoT) to explicitly separate semantic guidance and reference association, reducing ambiguity in image–text interleaved prompts. It further applies reinforcement learning with a surrogate alignment reward to improve consistency between reasoning and generated images. Extensive experiments show that Re-Align outperforms prior methods on both in-context image generation and editing tasks.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Unified Thinker: A General Reasoning Modular Core for Image Generation (2026)
- Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models (2025)
- Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling (2025)
- ReasonEdit: Towards Reasoning-Enhanced Image Editing Models (2025)
- ReViSE: Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning (2025)
- Loom: Diffusion-Transformer for Interleaved Generation (2025)
- REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper