Skip to content
VLA 線 · 查看同日 AI 報告 →查看同日 AI 报告 →
VLA 研究日報 Pulsar
LIVE
— AI 線今日無資料 —— AI 线今日无资料 —

VLA 研究日報VLA 研究日报

共 24 篇

🔧 技術技术

VLA [Stanford University]

Masked Visual Actions for Unified World Modeling

Hadi Alzayer et al. · 提出掩码视觉动作(MVA)方法,使视频世界模型能更好地对齐动作信号。解决了世界模型中动作表征的关键瓶颈,对提升 VLA 预测能力有直接帮助。

VLA [Computer Science, New York University]

Lifting Embodied World Models for Planning and Control

Alex N. Wang et al. · 提出提升具身世界模型以支持高维动作空间的规划与控制。解决了复杂形态下动作指定困难的问题,为基于世界模型的 VLA 控制提供了新视角。

📖 背景閱讀背景阅读

VLA [Alaya Lab]

AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

AlayaWorld Team et al. · arXiv:2607.18367v1 Announce Type: new Abstract: Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly. It enable us to create customized, explorable, and continuously evolving virtual world from text, an image, or video. Realizing this vision requires four tightly coupled capabilities: interaction, persistent spatiotemporal con