AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
Presents novel reinforcement learning approach for generating visually appealing code-based designs, bridging visual aesthetics with code correctness.
AI Summary
Researchers introduce AesCode, a method that improves aesthetic code generation for visual artifacts by using decoupled cross-modal rewards from both code verifiers and visual language models.
Excerpt
Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how their choices of layout and color come together on the canvas, often limiting spatial planning and aesthetic quality. Image generators excel at visual design but can misrender requested content, making their outputs unreliable targets for direct reproduction. We therefore introduce AesCode, which gen