The paper defines the Figma2Code task, releases a curated multimodal dataset from real Figma files, and benchmarks MLLMs to reveal that visual fidelity is achievable but responsive layouts and maintainable code remain weak.
Independently identify and fix any potential issues related to layout, styling, semantic correctness, or component structure
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Figma2Code: Automating Multimodal Design to Code in the Wild
The paper defines the Figma2Code task, releases a curated multimodal dataset from real Figma files, and benchmarks MLLMs to reveal that visual fidelity is achievable but responsive layouts and maintainable code remain weak.