Paper Detail
Tianyi Xiong, Zhengyuan Yang, Xiaofei Wang, Chung-Ching Lin, Ruichun Ma, Kevin Lin, Zhendong Wang, Linjie Li, Chenxi Liu, Ruibo Chen, Ramani Duraiswami, Heng Huang, Lijuan Wang
Large vision-language models have shown strong progress in UI-to-code generation, yet their test-time self-evolution remains unstable. We first identify a fundamental obstacle, termed visual repair coupling: a local code edit may propagate through layout, style, and component dependencies, correcting one visual mismatch while degrading regions that were previously faithful. To address this issue, we present RubSE, a Rubric-guided Self-Evolution framework that uses rubrics to represent visual feedback as a structured visual-repair context. At each refinement round, RubSE generates typed candidate rubrics, selects one prioritized repair target, and stores previously selected rubrics as history, thereby steering each revision toward a well-scoped visual repair while discouraging repeated or over-broad changes. Evaluations across six VLMs and three UI-to-code benchmarks demonstrate that RubSE substantially outperforms naïve self-evolution in final-round and best-round settings, achieving more stable refinement trajectories and a higher trajectory-level performance ceiling. Further analysis shows that RubSE mitigates trajectory collapse by improving recovery from severe visual regressions, and that stronger rubric generators can transfer effective visual-repair guidance to weaker code improvers.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{xiong2026rubrics,
title = {Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation},
author = {Tianyi Xiong and Zhengyuan Yang and Xiaofei Wang and Chung-Ching Lin and Ruichun Ma and Kevin Lin and Zhendong Wang and Linjie Li and Chenxi Liu and Ruibo Chen and Ramani Duraiswami and Heng Huang and Lijuan Wang},
year = {2026},
abstract = {Large vision-language models have shown strong progress in UI-to-code generation, yet their test-time self-evolution remains unstable. We first identify a fundamental obstacle, termed visual repair coupling: a local code edit may propagate through layout, style, and component dependencies, correcting one visual mismatch while degrading regions that were previously faithful. To address this issue, we present RubSE, a Rubric-guided Self-Evolution framework that uses rubrics to represent visual fee},
url = {https://huggingface.co/papers/2608.24138},
keywords = {visual repair coupling, RubSE, rubric-guided self-evolution, typed candidate rubrics, visual-repair context, trajectory collapse, huggingface daily},
eprint = {2608.24138},
archiveprefix = {arXiv},
}
{}