AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

Zeyu Wang, Zilong Chen, Chenhui Gou, Feng Li, Chaorui Deng, Deyao Zhu, Kunchang Li, Weihao Yu, Haoqin Tu, Haoqi Fan, Cihang Xie

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs

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 VAE tokens alongside ViT tokens for editing (ablation)LightFusion · GEdit-ENoverall: 3.91 -> 5.61Improved
add VAE tokens alongside ViT tokens for editing (ablation)LightFusion · ImgEditoverall: 2.65 -> 3.57Improved
add ViT tokens alongside VAE tokens for editing (ablation)LightFusion · GEdit-ENoverall: 4.93 -> 5.61Improved
add ViT tokens alongside VAE tokens for editing (ablation)LightFusion · ImgEditoverall: 3.38 -> 3.57Improved
raise training timestep shift from 1 to 4 (ablation)LightFusion · DPG-Benchoverall: 76.67 -> 81.77Improved
raise training timestep shift from 1 to 4 (ablation)LightFusion · ImgEditoverall: 3.07 -> 3.57Improved
raise training timestep shift from 1 to 2 (ablation)LightFusion · DPG-Benchoverall: 76.67 -> 78.84Improved
raise training timestep shift from 1 to 2 (ablation)LightFusion · ImgEditoverall: 3.07 -> 3.36Improved
condition DiT block i on VLM block i (0% depth deep fusion) instead of only final VLM output (ablation)LightFusion · text-to-image and image editingbenchmark scoresImproved
hybrid ViT+VAE feature fusion rather than ViT-only conditioning (vs UniWorld-V1)LightFusion · GEdit-Bench-ENsemantic consistency: 4.93 -> 6.34Improved
deep Double Fusion model vs UniWorld-V1LightFusion · ImgEdit-Benchoverall: 3.26 -> 3.77Improved
Double Fusion with frozen understanding branchLightFusion · MMBench/MMMU/MM-Vetaccuracy: 83.5, 58.6, 67.1No clear effect

Later papers that compared with this method

1 later accepted paper reports LightFusion as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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