AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Semantic Generative Tuning for Unified Multimodal Models

Songsong Yu, Yuxin Chen, Ying Shan, Yanwei Li

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 1 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 segmentation as generative proxy (SGT) alongside SFTBAGEL · CV-Benchaccuracy: 73.21 -> 79.23Improved
add segmentation as generative proxy (SGT) alongside SFTOmniGen2 · MMVPaccuracy: 65.00 -> 68.33Improved
add segmentation proxy vs pixel reconstruction proxy (ablation)BAGEL · CV-Benchaccuracy: 75.23 -> 79.23Improved
add segmentation proxy vs edge-detection proxy (ablation)OmniGen2 · MMStaraccuracy: 55.53 -> 57.07Improved
use SFT data alone without generative proxy (ablation)BAGEL · GenEvalscore: 78.21 -> 77.18Hurt
add any generative proxy (edge, reconstruction, segmentation) to SFT (ablation)BAGEL · GenEvalscore: 77.18 -> 80.95Improved
add segmentation proxy to SFT (ablation)BAGEL · GEdit-Bench-Enscore: 6.49 -> 6.94Improved
add segmentation proxy to SFT (ablation)BAGEL · MMVPaccuracy: 83.00 -> 83.33No clear effect
mix panoptic, reconstruction and edge tasks instead of segmentation alone (ablation)BAGEL · Understanding average (12 benchmarks)overall average: 75.8 -> 74.9Hurt
generative tuning with low-level edge or derain tasks only (ablation)BAGEL · Understanding average (12 benchmarks)overall average: 74.8 -> 74.4No clear effect
generative tuning with proxy tasks (no VQA) (ablation)BAGEL · OCRBench / MathVistaaccuracy: MathVista 72.2 -> 69.8 (+Semantic)Hurt
set segmentation-to-VQA mixing ratio to 2:1 (ablation)BAGEL and OmniGen2 · aggregate understanding scorenormalized scoreImproved

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