arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.13142cs.CVcs.AIcs.CL
收藏

TVWorld: 电视遥控的基石

TVWorld: Foundations for Remote-Control TV Agents

The University of Hong Kong(香港大学);Hong Kong Baptist University(香港 Baptist 大学);TCL Corporate Research (Hong Kong) Co., Ltd(TCL 香港企业研究有限公司)

Zhantao Ma, Quanfeng Lu, Shuai Zhong, Dahai Yu, Ping Luo, Michael K. Ng

AI总结:

TVWorld提出了一种基于图的电视导航抽象,开发了TVWorld-N和TVWorld-G两个基准测试,通过拓扑感知训练框架TVTheseus实现了68.3%的成功率,超越现有基线。

摘要:

最近的大型视觉-语言模型(LVLMs)在设备控制方面展示了强大的潜力。然而,现有研究主要集中在点击选择(PnC)交互上,而日常电视使用中常见的遥控(RC)交互仍 largely 未被探索。为了填补这一空白,我们引入了TVWorld,一种基于图的离线抽象,用于真实世界电视导航,使可重复和无部署的评估成为可能。在此基础上,我们推导出两个互补的基准测试,全面评估电视使用能力:TVWorld-N用于拓扑感知导航,TVWorld-G用于关注感知接地。这些基准测试揭示了现有代理的一个关键限制:在基于关注的长周期电视导航中拓扑感知不足。受这一发现的启发,我们提出了拓扑感知训练框架,将拓扑感知注入到LVLMs中。使用该框架,我们开发了TVTheseus,一种专门用于电视导航的基础模型。TVTheseus在TVWorld-N上的成功率为68.3%,超过了强大的闭源基线如Gemini 3 Flash,并建立了最先进的性能。进一步的分析还为有效电视使用代理的发展提供了有价值的见解。

英文摘要:

Recent large vision-language models (LVLMs) have demonstrated strong potential for device control. However, existing research has primarily focused on point-and-click (PnC) interaction, while remote-control (RC) interaction commonly encountered in everyday TV usage remains largely underexplored. To fill this gap, we introduce \textbf{TVWorld}, an offline graph-based abstraction of real-world TV navigation that enables reproducible and deployment-free evaluation. On this basis, we derive two complementary benchmarks that comprehensively assess TV-use capabilities: \textbf{TVWorld-N} for topology-aware navigation and \textbf{TVWorld-G} for focus-aware grounding. These benchmarks expose a key limitation of existing agents: insufficient topology awareness for focus-based, long-horizon TV navigation. Motivated by this finding, we propose a \emph{Topology-Aware Training} framework that injects topology awareness into LVLMs. Using this framework, we develop \textbf{TVTheseus}, a foundation model specialized for TV navigation. TVTheseus achieves a success rate of $68.3\%$ on TVWorld-N, surpassing strong closed-source baselines such as Gemini 3 Flash and establishing state-of-the-art (SOTA) performance. Additional analyses further provide valuable insights into the development of effective TV-use agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑