AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

CORE-V: Chain-Of-thought REasoning for Image Editing with Visual Interaction

Tianyang Yan, Peisen Zhao, Guanghao Zheng, Mingxing Xu, Zhibo Zhang, Wenrui Dai, Junni Zou, Hongkai Xiong, Xiaopeng Zhang, Qi Tian

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
use pretrained MLLM encoder instead of CLIP (ablation)CORE-V · Reason-EditPSNR: 21.307 -> 23.257Improved
add textual CoT reasoning (ablation)CORE-V with MLLM encoder · Reason-EditPSNR: 23.257 -> 23.544Improved
add visual imagination (reference images) (ablation)CORE-V · Reason-EditPSNR: 23.544 -> 25.012Improved
add spatial control (mask, depth, edge) (ablation)CORE-V · Reason-EditPSNR: 25.012 -> 24.567Mixed
add spatial control (mask, depth, edge) (ablation)CORE-V · Reason-EditSSIM: 0.858 -> 0.880Improved
add spatial control (mask, depth, edge) (ablation)CORE-V · Reason-EditCLIP: 22.46 -> 22.89Improved
raise lambda_edit from 2.5 to 3.0 (ablation)CORE-V · Emu-EditCLIPout: 0.313 -> 0.309Hurt
raise lambda_edit from 2.5 to 4.0 (ablation)CORE-V · Emu-EditCLIPout: 0.313 -> 0.297Hurt
reduce lambda_ref from 1.0 to 0.6 (ablation)CORE-V · Emu-EditDINO: 0.885 -> 0.865Hurt
reduce lambda_ref from 1.0 to 0.8 (ablation)CORE-V · Emu-EditDINO: 0.885 -> 0.880Hurt
CORE-V visual CoT vs BAGELCORE-V · Reason-Edit (reasoning)PSNR: 27.331 -> 28.356Improved
CORE-V vs BAGEL at context levelCORE-V · CORE-Bench (context level)CLIPDelta x100: 7.565 -> 7.901Improved

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