Skip to content
AI Atlas

LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents

Published 16 Sept 2026arXiv:2609.13287

data quality74

Updated 12 h ago · first seen 9 Sept 2026

paper_01M2HN8YAKDED22HZFWSRB6QMQ

Abstract

Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive for latency-sensitive applications. GUI agents represent a natural testbed for this paradigm, as they must repeatedly perceive screen states and emit structured, spatially grounded actions in real time. However, whether dLLMs can be extended into capable multimodal GUI agents while preserving their parallel decoding advantage remains an open question. We present LLaDA-UI, a 16.7B-parameter MoE-based, block-wise diffusion vision-language GUI agent. LLaDA-UI follows a two-stage training pipeline: general multimodal pre-training aligns a native-resolution vision encoder with the LLaDA2.0-mini-base diffusion language backbone, followed by GUI-agent supervised fine-tuning on diverse mobile, desktop, web, and grounding data. Across widely adopted grounding benchmarks and navigation benchmarks spanning multiple platforms, LLaDA-UI substantially outperforms Qwen2.5-VL-7B and surpasses Qwen3-VL-8B on four of six reported GUI benchmarks. These results establish block-wise diffusion as a practical generative paradigm for multimodal GUI agents.

Authors

Authors 20

Beitong ZhouChanghua MengChanglong GaoHaoxing ChenHaoyuan WuJianguo LiKai GanLin LiuLong CuiQi QinRongchao ZhangShuheng ShenWeiqiang WangWeizhi ChenXiaomei WangYi XinYunzhu ZhangZhangxuan GuZhengwen ZengZhenzhong Lan

Linked names open researcher pages (created from the paper's author list; name-only, no affiliation unless a source states it). Unlinked names have no researcher record yet.

Organizations

Organizations 0

No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.

Models

Models introduced or described 0

Inbound described_by relations from model cards and documentation.

No model links this paper yet

Model pages link papers through their model cards and documentation; the relation is written only when a source states it.

Datasets

Datasets used 0

No dataset relation recorded.

Benchmarks

Benchmarks used 0

No benchmark relation recorded.

Code

Repositories & frameworks 0

No repository linked.

Timeline

Timeline 4

Full timeline →

Sources

Sources 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
arXiv (Atom API + RSS)rss.arxiv.org/rss/cs.CV feedT1· Official2 h ago4
arXiv (Atom API + RSS)rss.arxiv.org/rss/cs.AI feedT1· Official2 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/papers listingT2· Quality secondary51 min ago32

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.