Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

[Submitted on 17 Jan 2026 (v1), last revised 25 Aug 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract:While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by the difficulty of synthesizing scientifically rigorous images. Existing Text-to-Image (T2I) models often produce outputs that are visually plausible yet scientifically incorrect, resulting in a persistent visual-logic divergence that limits their value for downstream reasoning. Motivated by recent advances in next-generation T2I models, we conduct a systematic study of scientific image synthesis across generation paradigms, evaluation, and downstream use. We analyze both direct pixel-based generation and programmatic synthesis, and propose ImgCoder, a logic-driven framework that follows an explicit “understand – plan – code” workflow to improve structural precision. To rigorously assess scientific correctness, we introduce SciGenBench, which evaluates generated images based on information utility and logical validity. Our evaluation reveals systematic failure modes in pixel-based models and highlights a fundamental expressiveness-precision trade-off. Finally, we show that fine-tuning Large Multimodal Models (LMMs) on rigorously verified synthetic scientific images yields consistent reasoning gains, with potential scaling trends analogous to the text domain, validating high-fidelity scientific synthesis as a viable path to unlocking massive multimodal reasoning capabilities.

Submission history

From: Honglin Lin [view email]
[v1] Sat, 17 Jan 2026 14:18:36 UTC (24,399 KB)
[v2] Tue, 25 Aug 2026 15:26:55 UTC (24,598 KB)