AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Unlocking Complex Image Editing via Natively Interleaved Visual Textual CoT with Deep Confidence Reasoning

Zhentao Zou, Zhengrong Yue, Kunpeng Du, Binglei Bao, Hanting Li, Haizhen Xie, Guozheng Xu, Yue Zhou, jie hu, Xue Jiang, Xinghao Chen

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add interleaved text-image CoT to text-only CoT (ablation)BAGEL · MagicBrush testL1: 0.067 -> 0.058Improved
add MMDC deep confidence reasoning (width 5) on top of interleaved CoT (ablation)MURE · MagicBrush testL1: 0.058 -> 0.049Improved
add MMDC to interleaved CoT (ablation)MURE · Emu Edit testDINO: 0.836 -> 0.897Improved
add MMDC to interleaved CoT (ablation)MURE · Emu Edit testCLIP-Out: 0.303 -> 0.301No clear effect
increase MMDC search width from 1 to 5 (ablation)MURE · Emu Edit testCLIP-I: 0.880 -> 0.920Improved
increase MMDC search width from 1 to 3 (ablation)MURE · MagicBrush testL1: 0.058 -> 0.052Improved
use interleaved CoT instead of text CoT on challenging MagicBrush subset (ablation)MURE w/o MMDC · MagicBrush challenging subsetL1: 0.081 -> 0.063Improved
add MMDC on challenging MagicBrush subset (ablation)MURE · MagicBrush challenging subsetL1: 0.063 -> 0.052Improved
use interleaved CoT instead of text CoT on SmartEdit spatial reasoning (ablation)MURE w/o MMDC · SmartEdit Spatial ReasoningPSNR: 23.823 -> 25.230Improved
add MMDC on SmartEdit spatial reasoning (ablation)MURE · SmartEdit Spatial ReasoningPSNR: 25.230 -> 25.610Improved
force interleaved CoT inference for object size changeMURE · MagicBrush test Obj.Size Chg.L1: 0.0499 -> 0.0479Improved
replace human scoring with Qwen-VL reward for MMDC on background changeMURE + MMDC · MagicBrush (121 cases) Bg. Chg.L1: 0.0585 -> 0.0581No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy