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 38 篇

⚡ 突破

🔧 技術技术

VLA

Reinforcing Action Policies by Prophesying

Jiahui Zhang et al. · 引入强化学习通过“预言”机制修正纯模仿学习的过拟合问题,提升分布外鲁棒性。为VLA的后训练阶段提供了结合RL的有效范式,有助于解决长尾失败案例。

📖 背景閱讀背景阅读

VLA [School of Information Science and Technology ShanghaiTech University]

Near-sensor Computing for Rapid Visuotactile Perception

Zhengying Zhu et al. · 关注近传感器计算以降低触觉感知延迟,属于硬件/边缘计算优化。虽对触觉VLA有潜在价值,但未涉及算法层面的VLA集成或性能提升。

VLA

Energy-Guided Flow Matching

Haoyang Tong (MAIS & NLPR et al. · 像素空间生成模型的能耗引导流匹配,侧重生成质量。虽可用于数据增强,但非VLA核心控制算法,应用路径间接。

VLA [University of Maryland College Park]

VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models

Ruiqi Xian et al. · arXiv:2606.13460v3 Announce Type: replace Abstract: Semantic 3D occupancy provides a voxelized world state for autonomous driving and robot decision making, but object and rare-class errors can affect free-space interpretation, collision checking, and temporal state propagation. We show that a common VLM strategy, aligning 3D voxel or object features with crop-caption embeddings, improves text-space similarity without reliably improving closed-set occupancy mIoU. Motivated by this mismatch, we p

VLA [Youngstown State University]

Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics

Hailong Jiang et al. · arXiv:2608.05371v1 Announce Type: new Abstract: World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing world models represent these states using classical vectors, probability distributions, recurrent hidden states, or transformer activations. In this paper, we introduce Quantum-Structured World Models (QSWMs), a quantum-inspired framework for predictive world modeling with structured latent states,