AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Charts Are Not Images: On the Challenges of Scientific Chart Editing

Li Li, Ryan A. Rossi, Sungchul Kim, Sunav Choudhary, Franck Dernoncourt, Puneet Mathur, Zhengzhong Tu, Yue Zhao

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 8 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
compare Imagen 4 SSIM against its instruction scoreImagen 4 · FigEdit Single editSSIM vs instruction score: SSIM 0.7726 vs instruction 1.58Mixed
use GPT-Image instead of Imagen 4 for conversational editsImagen 4 · FigEdit Conversational editinstruction-following score: 1.35 -> 4.59Improved
use GPT-Image instead of Imagen 4 for conversational edits (SSIM)Imagen 4 · FigEdit Conversational editSSIM: 0.7180 -> 0.6732Hurt
use OmniGen2 instead of InstructPix2Pix on single editsInstructPix2Pix · FigEdit Single editinstruction-following score: 3.27 -> 3.35No clear effect
use OmniGen2 instead of GPT-Image on visual guidanceGPTImage · FigEdit Visual guidanceinstruction-following score: 2.39 -> 1.19Hurt
use OmniGen2 instead of GPT-Image on style transferGPTImage · FigEdit Style transferinstruction-following score: 3.06 -> 1.53Hurt
go from single to multi editsImagen 4 · FigEditinstruction-following score: 1.58 -> 1.26Hurt
go from single to multi editsOmniGen2 · FigEditinstruction-following score: 3.35 -> 2.65Hurt
go from single to multi editsGPTImage · FigEditinstruction-following score: 3.47 -> 2.51Hurt
use GPT-Image on style transfer vs singleGPTImage · FigEditSSIM and instruction score: SSIM 0.7295 -> 0.8438; instruction 3.47 -> 3.06Mixed

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