AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MANGO: Unleashing Image Generation Capability of Unified Multimodal Models

Yi Wang, Mushui Liu, Wanggui He, Hanyang Yuan, Ziwei Huang, Guanghao Zhang, Wenkai Fang, Haoze Jiang, Shengxuming Zhang, Weilong Dai, Haofei Zhang, Mingli Song and 2 more

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 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 Paint-CoT planning and acting (dense caption + layout) over best-of-two T2I (ablation)MANGO 1.3B · GenEvaloverall: 0.67 -> 0.73Improved
add reflection and correction on top of planning and acting (ablation)MANGO 1.3B · GenEvaloverall: 0.73 -> 0.77Improved
add reflection and correction on top of planning and acting (ablation)MANGO 1.3B · T2I-CompBenchoverall: 50.62 -> 54.85Improved
add Paint-CoT full process vs T2I twice (ablation)MANGO 1.3B · GenEvalposition: 0.40 -> 0.60Improved
use functionality-oriented transformers (FoT) instead of dense design (ablation)MANGO · MS-COCOFID: 11.3 -> 7.24Improved
use FoT instead of modality-oriented design (ablation)MANGO · MS-COCOFID: 9.56 -> 7.24Improved
use FoT instead of modality-oriented design (ablation)MANGO · MS-COCOCIDEr: 121.1 -> 126.5Improved
full Paint-CoT vs T2I generation on aesthetic score (ablation)MANGO 1.3B · Aesthetic Scoreaesthetic score: 5.98 -> 6.04No clear effect
full Paint-CoT vs T2I generation on human preference (ablation)MANGO 1.3B · HPS v2win rate (%): 62.3Improved
run a second reflection-correction cycle (ablation)MANGO 1.3B · GenEvaloverallNo clear effect
scale backbone from Qwen2-0.5B to Qwen2-1.5B (MANGO-4B)MANGO · GenEvaloverall: 0.77 -> 0.82Improved
scale backbone from Qwen2-0.5B to Qwen2-1.5B (MANGO-4B)MANGO · T2I-CompBench Complexscore: 42.78 -> 45.29Improved

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