# DuplexBridge: Coordinating Understanding and Generation for Unified Image Editing

arXiv: https://arxiv.org/abs/2610.18819 · HTML: https://mlsanity.com/paper/2610.18819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 28 of 28)

- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [ImgEdit: A Unified Image Editing Dataset and Benchmark](https://mlsanity.com/paper/2505.20275/) (2025)
- [WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2503.07265/) (2025)
- [Guiding Instruction-based Image Editing via Multimodal Large Language Models](https://mlsanity.com/paper/2309.17102/) (2023)
- [SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models](https://mlsanity.com/paper/2312.06739/) (2023)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Self-correcting LLM-controlled Diffusion Models](https://mlsanity.com/paper/2311.16090/) (2023)
- [Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing](https://mlsanity.com/paper/2504.02826/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models](https://mlsanity.com/paper/2505.16707/) (2025)
- [RewardDance: Reward Scaling in Visual Generation](https://mlsanity.com/paper/2509.08826/) (2025)
- [EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing](https://mlsanity.com/paper/2509.26346/) (2025)
- [GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation](https://mlsanity.com/paper/2512.16853/) (2025)
- [R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation](https://mlsanity.com/paper/2505.23493/) (2025)
- [Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image](https://mlsanity.com/paper/2512.16899/) (2025)
- [Wan-Image: Pushing the Boundaries of Generative Visual Intelligence](https://mlsanity.com/paper/2604.19858/) (2026)
- [GEditBench v2: A Human-Aligned Benchmark for General Image Editing](https://mlsanity.com/paper/2603.28547/) (2026)
- [ThinkGen: Generalized Thinking for Visual Generation](https://mlsanity.com/paper/2512.23568/) (2025)
- [ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing](https://mlsanity.com/paper/2601.03467/) (2026)
- [Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning](https://mlsanity.com/paper/2605.21487/) (2026)
- [Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process](https://mlsanity.com/paper/2607.03748/) (2026)
- [Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions](https://mlsanity.com/paper/2606.09076/) (2026)
- [DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing](https://mlsanity.com/paper/2604.25477/) (2026)
- [DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing](https://mlsanity.com/paper/2608.20161/) (2026)

## Abstract (arXiv)

Complex image editing requires faithful task interpretation and accurate execution, but a failed edit does not reveal which responsibility failed. We present DuplexBridge, which uses a unified model's own understanding capability to enhance prompts for its own generation capability, without an external understanding module. A source-grounded bridge specifies targets, final-state changes, and preservation constraints. Understanding is supervised on fidelity to the original request without observing the generated image; generation is supervised on execution of the condition it actually receives. Reciprocal trust checks selectively admit global task feedback to each role while retaining independently valid local supervision. We introduce CE-Bench, a 1,200-task benchmark measuring joint satisfaction of task-derived change and preservation requirements. Across three model configurations, the full system improves complete compliance over direct editors by 21.75-25.75 percentage points, with gains also observed on KRIS-Bench, RISEBench, ImgEdit, and GEdit-Bench. From a common supervised Wan-Image initialization, gated joint training reaches 77.08% complete compliance, compared with 70.92% without gates and 75.00% when generation-local supervision instead checks the original task with both gates retained. These results support distinct local responsibilities and selective shared feedback for joint understanding-generation adaptation.