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 2511.05936cs.ROcs.AI
收藏

引领视觉-语言-动作模型未来的十大开放挑战

10 Open Challenges Steering the Future of Vision-Language-Action Models

Soujanya Poria, Navonil Majumder, Chia-Yu Hung, Amir Ali Bagherzadeh, Chuan Li, Kenneth Kwok, Ziwei Wang, Cheston Tan, Jiajun Wu, David Hsu

AI总结:

本文梳理了视觉-语言-动作模型发展中的十大核心挑战,并指出空间理解、世界动态建模、后训练与数据合成等新兴趋势是推动其走向更广泛应用的关键路径。

摘要:

由于具备遵循自然语言指令的能力,视觉-语言-动作(VLA)模型在具身人工智能领域日益普及,这得益于其前身——大语言模型(LLM)和视觉-语言模型(VLM)——的广泛成功。在本文中,我们讨论了VLA模型持续发展中的10个主要里程碑——多模态、推理、数据、评估、跨机器人动作泛化、效率、全身协调、安全性、智能体以及与人协作。此外,我们讨论了利用空间理解、世界动态建模、后训练和数据合成的新兴趋势——这些均旨在达成上述里程碑。通过这些讨论,我们希望引起人们对可能加速VLA模型发展并使其获得更广泛接受的研究方向的关注。

英文摘要:

Due to their ability of follow natural language instructions, vision-language-action (VLA) models are increasingly prevalent in the embodied AI arena, following the widespread success of their precursors -- LLMs and VLMs. In this paper, we discuss 10 principal milestones in the ongoing development of VLA models -- multimodality, reasoning, data, evaluation, cross-robot action generalization, efficiency, whole-body coordination, safety, agents, and coordination with humans. Furthermore, we discuss the emerging trends of using spatial understanding, modeling world dynamics, post training, and data synthesis -- all aiming to reach these milestones. Through these discussions, we hope to bring attention to the research avenues that may accelerate the development of VLA models into wider acceptability.

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。

↑