AI
VLA 视觉语言动作模型
定义待编辑审核。
机器人领域的VLA 视觉语言动作模型：已记录 7 家公司、58 篇论文和 51 篇报道，包括Figure AI、Galbot、Physical Intelligence、另外 4 家。
公司
7
相关公司融资
27.9亿美元
论文
10
报道
10
布局该技术的公司
推动该技术的论文
- EqC: Equilibrium Energy Control for Introspective Lifelong Robot Learning
- DR-VLA: Learning Human-Like Quadruped Navigation from Egocentric Web Videos via Domain-Invariant Scene Representations
- Benchmarking Interaction-Oriented Aerial Mobility across Heterogeneous Environments
- Breaking the Average: Overcoming Convergent Defaults in Robotic Manipulation via Diagnostic Chain-of-Thought and Structured Guidance
- WoVR+: World Model as Reliable Simulator for Versatile VLA Policy Optimization with RL
- The Human--VLA Communication Gap: What Humans Leave Implicit and What Policies Cannot Recover
- ChunkAct: Action Chunking for Agentic Robotics
- What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study
- EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence
- LIBERO-RIG: A Hardware-Setup Robustness Benchmark for Vision-Language-Action Models