AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

FontCopilot: Towards Generalist Multimodal Large Language Models for Holistic Chinese Font Engineering

Yu Liu, Yang Liu, Ying Gao, Yang Ding, Cunrui Wang

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Language models for zero-shot 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 FontCopilot SVG-code MLLM instead of instruction-tuned Qwen3-VL-8Bglyph vectorization · Glyph vectorizationIoU: 0.865 -> 0.925Improved
use FontCopilot instead of non-learning tracing tools for raster fidelityglyph vectorization · Glyph vectorizationIoU / CD: IoU 0.982 (AIT) vs 0.925; CD 0.0041 vs 0.0355Hurt
use FontCopilot for node compression instead of Qwen3-VL-8Bvector optimization · Vector optimizationReduction Ratio (%): 71.88 -> 76.52Improved
use FontCopilot for defect detectiondefect detection · Defect detectionIoU: 0.875 -> 0.938Improved
use FontCopilot for geometric correctiongeometric correction · Geometric correctionIoU: 0.825 -> 0.908Improved
replace manual refinement with FontCopilot outputsfont production · Human evaluationfix time (s): 184.1 -> 24.5Improved
raise number of few-shot reference glyphs K beyond 3 (ablation)FontCopilot · Reference count sensitivity K 0-8geometric errorNo clear effect
raise visual injection layer count L beyond 3 (ablation)FontCopilot · Injection layers L 0-8geometric errorHurt
use graphics-based methods vs FontCopilot for raster-to-vector accuracyPotrace/AIT · Human evaluation Vrating (1-5): 4.15 (AIT) vs 4.12 (FontCopilot)Mixed

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