media creative tools
The Code Generator Gets Judged by the Canvas
AesCode separates verifiable content from visual quality when generating editable slides, posters and dashboards as code.
Summary
AesCode separates verifiable content from visual quality when generating editable slides, posters and dashboards as code.
Code can produce structured, editable visual artifacts, but a language model may not see how its layout and color choices render. AesCode supplies an image generated from the same prompt as aesthetic guidance, represents the target as a design graph and separates rewards: deterministic checks cover properties that code and rendering can verify, while a vision-language judge scores harder visual relations with a sample-specific rubric. The authors report visual-quality gains of 31.1 and 22.4 percentage points for their 8B and 32B models over same-scale baselines with the same references. Those scores come from the new benchmark and its judging protocol. The system's central move is to keep factual correctness and appearance as distinct optimization channels.
Why it matters
AesCode separates verifiable content from visual quality when generating editable slides, posters and dashboards as code.
Limits and context
- Code can produce structured, editable visual artifacts, but a language model may not see how its layout and color choices render.
Key claims
AesCode separates verifiable content from visual quality when generating editable slides, posters and dashboards as code.
Qualification: Code can produce structured, editable visual artifacts, but a language model may not see how its layout and color choices render.
Evidence: source-2026-10-14-008
Sources
- arXiv preprint 2610.18860, original v1arXiv / submitting research authors · primary research
Corrections
No corrections have been recorded for this story.