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.</p>\n","updatedAt":"2026-05-25T01:56:36.475Z","author":{"_id":"63859cf3b2906edaf83af9f0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63859cf3b2906edaf83af9f0/kajwuVzd4pDucSPlwghxo.png","fullname":"Yuhang Zang","name":"yuhangzang","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":22,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9171091318130493},"editors":["yuhangzang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/63859cf3b2906edaf83af9f0/kajwuVzd4pDucSPlwghxo.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.23897","authors":[{"_id":"6a13ac004d9e8d8602d201f1","name":"Beichen Zhang","hidden":false},{"_id":"6a13ac004d9e8d8602d201f2","name":"Yuhong Liu","hidden":false},{"_id":"6a13ac004d9e8d8602d201f3","name":"Jinsong Li","hidden":false},{"_id":"6a13ac004d9e8d8602d201f4","name":"Yuhang Zang","hidden":false},{"_id":"6a13ac004d9e8d8602d201f5","name":"Jiaqi Wang","hidden":false},{"_id":"6a13ac004d9e8d8602d201f6","name":"Dahua Lin","hidden":false}],"publishedAt":"2026-05-22T00:00:00.000Z","submittedOnDailyAt":"2026-05-25T00:00:00.000Z","title":"ETCHR: Editing To Clarify and Harness Reasoning","submittedOnDailyBy":{"_id":"63859cf3b2906edaf83af9f0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63859cf3b2906edaf83af9f0/kajwuVzd4pDucSPlwghxo.png","isPro":true,"fullname":"Yuhang Zang","user":"yuhangzang","type":"user","name":"yuhangzang"},"summary":"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.","upvotes":6,"discussionId":"6a13ac014d9e8d8602d201f7","githubRepo":"https://github.com/InternLM/ETCHR","githubRepoAddedBy":"user","ai_summary":"A novel image editing approach called ETCHR is introduced that decouples visual reasoning from image generation, improving multimodal language model performance across multiple visual reasoning tasks through a two-stage training process.","ai_keywords":["Multimodal Large Language Models","visual reasoning","chain of thought","think with images","image editing model","decoupled architecture","reasoning-aware image editor","Reasoning Imitation","Reasoning Enhancement","VLM-derived rewards","Pass@1","Qwen3-VL-8B","Gemini-3.1-Flash-Lite","Kimi K2.5"],"githubStars":6,"organization":{"_id":"64a2d5fa81252883206f24c9","name":"internlm","fullname":"Intern Large Models","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6432683407bad11484a68457/Q3Y0dL79GcsnaBCGRMooZ.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63859cf3b2906edaf83af9f0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63859cf3b2906edaf83af9f0/kajwuVzd4pDucSPlwghxo.png","isPro":true,"fullname":"Yuhang Zang","user":"yuhangzang","type":"user"},{"_id":"64b93578ee257c3a4cfceed1","avatarUrl":"/avatars/e6188562254f75a09b4048b800860016.svg","isPro":false,"fullname":"Beichen Zhang","user":"BeichenZhang","type":"user"},{"_id":"65ab5332043d53781a115475","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65ab5332043d53781a115475/UaxSFDWteYsByzx7G_KKy.jpeg","isPro":false,"fullname":"Zhixiong Zhang (SII)","user":"rookiexiong","type":"user"},{"_id":"64f5964a413ca787f12b8ade","avatarUrl":"/avatars/e4b65c19b92e50d93e3137468a58c96a.svg","isPro":false,"fullname":"Yang Penghui","user":"ygyjrc","type":"user"},{"_id":"66fb03d6b505f1a04c39d935","avatarUrl":"/avatars/e9b830c460ec02037758c9b3469bb8ad.svg","isPro":false,"fullname":"Xuanlang Dai","user":"XuanlangDai","type":"user"},{"_id":"63c1699e40a26dd2db32400d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63c1699e40a26dd2db32400d/3N0-Zp8igv8-52mXAdiiq.jpeg","isPro":false,"fullname":"Chroma","user":"Chroma111","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"64a2d5fa81252883206f24c9","name":"internlm","fullname":"Intern Large Models","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6432683407bad11484a68457/Q3Y0dL79GcsnaBCGRMooZ.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.23897.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2605.23897 in a Space README.md to link it from this page.