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 37 篇

⚡ 突破

🔧 技術技术

📖 背景閱讀背景阅读

VLA [Zhejiang University of Science and Technology]

DLAM: Distributional Latent Actions with Temporal Constraints

Zuojin Tang et al. · 提出带时间约束的分布潜在动作模型,利用无动作标签视频。方法偏向表示学习,虽有助于缓解数据稀缺,但未明确展示其在VLA端到端训练中的架构优势。

VLA [State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology]

FasTac: A Curved Multispectral Vision-Based Tactile Sensor for High-Speed High-Precision 3D Shape and Force Perception

Xiaofan Lu et al. · 介绍新型曲面多光谱视觉触觉传感器FasTac。属硬件传感创新,虽为VLA提供数据源,但非算法或模型层面的进展,归为值得了解的硬件配套。

VLA [New York University]

What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations

Kaizhen Tan et al. · arXiv:2607.27017v2 Announce Type: replace-cross Abstract: A central premise of latent world models is that predicting the future forces a representation to internalize the physics of its environment. Which physical quantities does a trained latent actually contain, and what decides this? We answer with controlled interventions in POKEWORLD, an interactive environment whose visually identical objects hide mass, drag, and contact stiffness. A certificate-gated protocol first certifies each paramet