ETCHR: Editing To Clarify and Harness Reasoning

• URL: http://arxiv.org/abs/2605.23897v1
• Date: Fri, 22 May 2026 17:58:28 GMT
• Title: ETCHR: Editing To Clarify and Harness Reasoning
• Abstract summary: We introduce ETCHR (Editing To Clarify and Harness Reasoning), a question-conditioned, reasoning-aware image editor.<n>It is trained with a two-stage recipe targeted at the two gaps: Reasoning Imitation via supervised fine-tuning on edit trajectories, and Reasoning Enhancement with VLM-derived rewards for edit correctness and downstream reasoning accuracy.<n>Since the editor is decoupled, ETCHR plugs into different open- and closed-source MLLMs in a training-free manner.
• Score: 70.02956047187827
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models have advanced visual reasoning, yet a purely textual chain of thought remains a bottleneck for questions that require fine-grained focus or view transformations. The ''think with images'' paradigm narrows this gap, but existing approaches are either constrained by fixed predefined toolkits or produce noisy intermediate images from unified multimodal methods. We pursue a third option: using a dedicated image editing model and decouple it with an understanding model. However, off-the-shelf image editors fail as reasoning assistants with two complementary gaps: a language-side gap, where editors trained as passive instruction-followers cannot map an abstract question to an appropriate visual transformation, and a generation-side gap, where edit correctness degrades as reasoning depth grows. Guided by this analysis, we introduce ETCHR (Editing To Clarify and Harness Reasoning), a question-conditioned, reasoning-aware image editor decoupled from the downstream understanding model and trained with a two-stage recipe targeted at the two gaps: Reasoning Imitation via supervised fine-tuning on edit trajectories, followed by Reasoning Enhancement with VLM-derived rewards for edit correctness and downstream reasoning accuracy. Since the editor is decoupled, ETCHR plugs into different open- and closed-source MLLMs in a training-free manner. Across five task families (fine-grained perception, chart understanding, logic reasoning, jigsaw restoration, and 3D understanding), ETCHR raises average Pass@1 from 55.95 to 60.77 (+4.82) with Qwen3-VL-8B, from 65.08 to 70.55 (+5.47) with Gemini-3.1-Flash-Lite, and from 76.55 to 81.16 (+4.61) with the 1T-parameter MoE model Kimi K2.5.

Related papers

• Self-Corrected Image Generation with Explainable Latent Rewards [55.29175717238288]
  We propose xLARD, a self-correcting framework that guides generation through Explainable LAtent RewarDs.<n>xLARD introduces a lightweight corrector that refines latent representations based on structured feedback from model-generated references.<n> Experiments show that xLARD improves semantic alignment and visual fidelity while maintaining generative priors.
  arXiv  Detail & Related papers  (2026-03-26T02:59:35Z)
• AdaEdit: Adaptive Temporal and Channel Modulation for Flow-Based Image Editing [10.474377498273205]
  Inversion-based image editing in flow matching models has emerged as a powerful paradigm for training-free, text-guided image manipulation.<n>Existing methods address this with fixed injection strategies that ignore the inherently heterogeneous nature of injection demand.<n>We present AdaEdit, a training-free adaptive editing framework that resolves this dilemma through two complementary innovations.
  arXiv  Detail & Related papers  (2026-03-23T06:22:53Z)
• Show, Don't Tell: Morphing Latent Reasoning into Image Generation [60.743575139661154]
  Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation.<n>We introduce LatentMorph, a framework that seamlessly integrates implicit latent reasoning into the T2I generation process.<n>By performing reasoning entirely in continuous latent spaces, LatentMorph avoids the bottlenecks of explicit reasoning and enables more adaptive self-refinement.
  arXiv  Detail & Related papers  (2026-02-02T15:29:48Z)
• ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing [33.888289858260706]
  Reinforcement learning (RL) has been investigated for improving the quality of image editing.<n>RL faces three key challenges: (1) limited reasoning exploration confined to denoising, (2) biased reward fusion, and (3) unstable VLM-based instruction rewards.<n>We propose ThinkRL-Edit, a reasoning-centric RL framework that decouples visual reasoning from image synthesis.
  arXiv  Detail & Related papers  (2026-01-06T23:43:00Z)
• ReasonEdit: Towards Reasoning-Enhanced Image Editing Models [60.902953259781675]
  A common architectural design couples a multimodal large language model (MLLM) encoder with a diffusion decoder.<n>We show that unlocking the reasoning capabilities of MLLM can push the boundaries of editing models.<n>Our proposed framework enables image editing in a thinking-editing-reflection loop.
  arXiv  Detail & Related papers  (2025-11-27T17:02:48Z)
• Visual Autoregressive Modeling for Instruction-Guided Image Editing [97.04821896251681]
  We present a visual autoregressive framework that reframes image editing as a next-scale prediction problem.<n>VarEdit generates multi-scale target features to achieve precise edits.<n>It completes a $512times512$ editing in 1.2 seconds, making it 2.2$times$ faster than the similarly sized UltraEdit.
  arXiv  Detail & Related papers  (2025-08-21T17:59:32Z)
• A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models [117.77807994397784]
  Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. Recent significant advancement in this field is based on the development of text-to-image (T2I) diffusion models. T2I-based image editing methods significantly enhance editing performance and offer a user-friendly interface for modifying content guided by multimodal inputs.
  arXiv  Detail & Related papers  (2024-06-20T17:58:52Z)
• Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion [35.95513392917737]
  A novel approach called Dual-Cycle Diffusion generates an unbiased mask to guide image editing. Our experiments demonstrate the effectiveness of the proposed method, as it significantly improves the D-CLIP score from 0.272 to 0.283.
  arXiv  Detail & Related papers  (2023-02-05T14:30:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.