English(EN) GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents

新的GUI-JEPA代理策略加速移动GUI交互

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了GUI-JEPA，一种新颖的无解码器GUI代理策略，它在联合嵌入预测架构（JEPA）的潜在空间内运行。与传统的微调视觉语言模型（VLMs）相比，这种方法显著提高了速度并降低了内存需求。GUI-JEPA通过在潜在空间中预测动作来实现这一点，允许通过单个批量传递对候选动作进行评分，而无需进行令牌解码。在AndroidControl上的测试中，GUI-JEPA在保持高精度的同时，比Qwen2.5-VL-7B代理快2.8-4.0倍，并且参数数量大大减少。 AI

影响引入了一种更高效的移动GUI代理架构，有望加快任务完成速度并降低资源需求。

排序理由这是一篇详细介绍新AI模型架构及其在特定基准上性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新AI模型架构及其在特定基准上性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Bingchao Wang, Yongcheng Jing, Shunyu Liu, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao · 2026-10-28 04:00

GUI-JEPA：候选条件JEPA潜在表示作为移动GUI代理的快速动作策略

arXiv:2610.36877v1 Announce Type: new Abstract: Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token, and even agents that score candidate actions keep a large l…

本文如何被排名

报道来源 [1]

GUI-JEPA：候选条件JEPA潜在表示作为移动GUI代理的快速动作策略

相关实体

相关话题