Metraipolis › archive › dc_bef801523ced

Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation — arXiv:2611.01692

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01692
License (as archived): CC0-1.0
Archived: 2026-11-03T10:57:20.748Z
SHA-256 of the archived text: f130f5cd609511a67f6799593bd61de751d487431d6ec052411971525484f559
Stable URL of this page: https://metraipolis.com/documento/dc_bef801523ced

How to cite

Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation — arXiv:2611.01692 — arXiv (en), https://arxiv.org/abs/2611.01692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bef801523ced (Metraipolis archive dc_bef801523ced, sha256 f130f5cd609511a67f6799593bd61de751d487431d6ec052411971525484f559)

BibTeX

@misc{dcbef801523ced,
  title = {Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation — arXiv:2611.01692},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01692},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bef801523ced; sha256 f130f5cd609511a67f6799593bd61de751d487431d6ec052411971525484f559},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language models (MLLMs) achieve strong performance in translating WebUI screenshots into HTML/CSS. However, when they faced multiple frameworks (React/Vue/Angular), they often suffer from negative transfer that leads to compilation failures. These failures commonly stem from mixing framework specific syntax and violating framework constraints. This paper studies supervised fine-tuning for multi-framework WebUI code generation and proposes a phase-wise MLLM tuning method driven by compatibility and heterogeneity signals across frameworks. We first apply a normalization mapping that preserves each framework's native syntax while suppressing noise from variable naming and literal content. We then estimate cross framework heterogeneity and compatibility offline, and automatically derive training groups and their ordering by maximizing a phased objective. Finally, we perform phase-wise adapter tuning to reduce cross framework interference. Experiments on multiple benchmarks show that our proposed method improves both generation quality and compilation success rate compared with baselines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01692 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:49:38.584Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).