AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework

Feiyu Wang, Jiayuan Yang, Zhiyuan Zhao, Da Zhang, Bingyu Li, Peng Liu, Junyu Gao

CVPR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 3 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 DPO on generation preferences (ablation)IntroSVG SFT model (no iteration) · Text-to-SVG benchmarkFID: 30.15 -> 29.76Improved
add SFT on mixed generation and critic data (ablation)Qwen2.5-VL-7B · Text-to-SVG benchmarkFID: 71.10 -> 30.15Improved
add SFT on mixed generation and critic data (ablation)Qwen2.5-VL-7B · Text-to-SVG benchmarkAesthetic: 4.32 -> 4.80Improved
add the iterative generate-critique-refine loop (3 iterations) (ablation)IntroSVG after SFT+DPO · Text-to-SVG benchmarkFID: 29.76 -> 26.18Improved
use absolute commands and integer coordinates instead of mixed commands and decimals (ablation)Qwen2.5-VL-3B SVG training data · SVG data standardization ablationFID: 121.50 -> 32.15Improved
use absolute instead of relative commands (integer precision) (ablation)Qwen2.5-VL-3B SVG training data · SVG data standardization ablationFID: 37.34 -> 32.15Improved
use integer instead of decimal coordinates (absolute commands) (ablation)Qwen2.5-VL-3B SVG training data · SVG data standardization ablationFID: 34.62 -> 32.15Improved
use integer instead of decimal coordinates (absolute commands) (ablation)Qwen2.5-VL-3B SVG training data · SVG data standardization ablationRSR%: 95.89 -> 98.62Improved
apply introspective loop as zero-shot prompting (Iter 0 to Iter 3)Grok-4 · Text-to-SVG benchmarkFID: 41.39 -> 32.85Improved
apply introspective loop as zero-shot prompting (Iter 0 to Iter 3)GPT-4o · Text-to-SVG benchmarkFID: 37.80 -> 36.34Improved
apply introspective loop as zero-shot prompting (Iter 0 to Iter 3)GPT-5 · Text-to-SVG benchmarkCLIP-T2I: 0.2858 -> 0.2779Mixed
add more refinement iterations (Iter 0 to Iter 3)IntroSVG · Text-to-SVG benchmarkFID: 29.76 -> 26.18Improved

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