Metraipolis › archive › dc_9e8de3bfbc23

UI-UG 2: Advancing Mobile UI Understanding and Generation with Fine-Grained Supervision and Reinforcement Learning — arXiv:2611.00926

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00926
License (as archived)
CC0-1.0
Archived
2026-11-03T10:46:12.252Z
SHA-256 of the archived text
bb75fd750bd1144a66c5d8070021e7ed2b963fd5004b54b3e8cb5a46b6606863
Stable URL of this page
https://metraipolis.com/documento/dc_9e8de3bfbc23

How to cite

UI-UG 2: Advancing Mobile UI Understanding and Generation with Fine-Grained Supervision and Reinforcement Learning — arXiv:2611.00926 — arXiv (en), https://arxiv.org/abs/2611.00926 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9e8de3bfbc23 (Metraipolis archive dc_9e8de3bfbc23, sha256 bb75fd750bd1144a66c5d8070021e7ed2b963fd5004b54b3e8cb5a46b6606863)
BibTeX
@misc{dc9e8de3bfbc23,
  title = {UI-UG 2: Advancing Mobile UI Understanding and Generation with Fine-Grained Supervision and Reinforcement Learning — arXiv:2611.00926},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00926},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9e8de3bfbc23; sha256 bb75fd750bd1144a66c5d8070021e7ed2b963fd5004b54b3e8cb5a46b6606863},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00926. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mobile UI understanding and generation require both fine-grained component perception and reliable structured synthesis. Inspired by the unified direction introduced by UI-UG, we present UI-UG 2, a compact 4B-parameter multimodal large language model (MLLM) that advances mobile UI Understanding and Generation with broader task coverage, a front-end-aligned taxonomy, and online render-aware reinforcement learning. UI-UG 2 constructs a multi-source understanding corpus from RICO, VINS, Android in the Wild, and Android Control, annotated with an 80-category two-level UI taxonomy aligned with front-end component semantics, and pairs it with over 5,000 requirement-screenshot-JSON tuples for progressive structured UI generation through a domain-specific language (DSL). For understanding, UI-UG 2 introduces decomposed rewards for category prediction, OCR fidelity, color recognition, dense grounding, and GUI grounding. Unlike the offline Direct Preference Optimization (DPO)-style generation optimization in UI-UG, UI-UG 2 optimizes generation through end-to-end online Group Relative Policy Optimization (GRPO): sampled DSL outputs are rendered with a Playwright-based server-side pipeline and evaluated using LLM-as-a-Judge and contrastive preference ranking. Experiments show that UI-UG 2 achieves the strongest referring and dense-grounding results among the evaluated models on our 80-category benchmark, and achieves the best composite generation score among compared models at a compact scale (4B). More importantly, we observe a consistent understanding-to-generation transfer: adding fine-grained UI perception supervision improves generation quality under a fixed training budget, suggesting that component-level semantics provide a shared representational foundation for both tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2611.00926 — 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 2026-11-03T10:39:50.438Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).