mlsanityData to 14 Oct 2026

DuplexBridge: Coordinating Understanding and Generation for Unified Image Editing

arXiv 2610.18819 ↗First posted 13 Oct 2026cs.CVcited by 0

Not on the map. Why?

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.

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

28 of 38 references.

References · 28

  1. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  2. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  3. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
  4. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  5. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  6. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 231
  7. 2025WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generationcited by 204
  8. 2023Guiding Instruction-based Image Editing via Multimodal Large Language Modelscited by 185
  9. 2023SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Modelscited by 177
  10. 2023Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generationcited by 171
  11. 2023Self-correcting LLM-controlled Diffusion Modelscited by 113
  12. 2025Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editingcited by 99
16 more
  1. 2025Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuningcited by 90
  2. 2025KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Modelscited by 71
  3. 2025RewardDance: Reward Scaling in Visual Generationcited by 68
  4. 2025EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editingcited by 62
  5. 2025GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluationcited by 52
  6. 2025R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generationcited by 32
  7. 2025Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Imagecited by 20
  8. 2026Wan-Image: Pushing the Boundaries of Generative Visual Intelligencecited by 16
  9. 2026GEditBench v2: A Human-Aligned Benchmark for General Image Editingcited by 14
  10. 2025ThinkGen: Generalized Thinking for Visual Generationcited by 13
  11. 2026ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editingcited by 12
  12. 2026Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuningcited by 6
  13. 2026Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Processcited by 5
  14. 2026Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributionscited by 4
  15. 2026DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editingcited by 3
  16. 2026DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editingcited by 1

Built on by

Not cited yet.