跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-12AI 評分45

InfoVis:統一投影片圖像生成與編輯模型

InfoVis: Unified Slide Image Generation and Editing

AI 導讀

InfoVis 是一個統一的 9B 投影片生成與編輯模型,在 VisSlideBench 的 11 項指標均領先所有受測開源模型,總分為 7.94,Nano-Banana-2 則為 7.99。模型以 FLUX.2-klein-base-9B 為基礎,投影片專項後訓練令總分提升 1.6 分。團隊將發布模型、程式碼、數據及基準測試集。

正文

Published on Oct 12

Authors:

,

,

,

,

,

,

,

,

Abstract

InfoVis is a unified 9B model for slide generation and editing trained on millions of native records and evaluated on a new multidimensional benchmark, achieving top open-source performance across text rendering, instruction following, visual grounding, design, and editing.

Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within one canvas. Existing work covers only subsets of these capabilities and lacks large-scale slide-native supervision and diagnostic evaluation. We formulate four slide-centric tasks and build a scalable data engine with over 13M continual-pretraining records and 1.9M supervised fine-tuning records. We also introduce VisSlideBench, a benchmark of 1,527 manually screened instances that covers all four tasks with task-specific, multidimensional evaluation. Its automatic rankings agree with blinded, dimension-wise human rankings. Using these resources, we train InfoVis, a unified 9B slide generation and editing model. On VisSlideBench, InfoVis leads every evaluated open-source model on all eleven metrics and scores 7.94 overall against 7.99 for Nano-Banana-2. Starting from FLUX.2-klein-base-9B, slide-specific post-training adds 1.6 points overall, with the largest generation gains in content faithfulness; the remaining gap to proprietary models is smallest in content faithfulness and largest in aesthetic quality. Built on InfoVis, our document-to-slide workflow achieves the second-highest Aesthetics score on the external SlidesGen-Bench. We will release the model, code, data, and benchmark.

View arXiv page View PDF Project page GitHub 2 Add to collection

Get this paper in your agent:

hf papers read 2610.16784

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

InfoVis/InfoVis

Text-to-Image •

9B •

Updated 1 day ago

•

26

•

3

Datasets citing this paper 2

InfoVis/Data

Viewer •

Updated 2 days ago

•

9.9M

•

956

•

2

InfoVis/VisSlideBench

Viewer •

Updated 2 days ago

•

1.53k

•

47

•

2

Spaces citing this paper 1

Collections including this paper 1

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co