AI
Vision-Language-Action Models
Definition pending editorial review.
Vision-Language-Action Models in robotics: 7 companies, 17 papers and 22 stories on record, including Figure AI, Galbot, Physical Intelligence, 4 more.
Companies
7
Funding across them
$2.79B
Papers
10
Stories
10
Companies building on it
Papers advancing it
- GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
- DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents
- PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors
- Multi-Link Safety Filtering for VLA Policies Around Moving Hazards
- EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action
- When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models
- Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation
- Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
- Inline Memory Meets Reusable Skills: Memory-centric Framework for Vision-Language-Action Model
- From Local Whole-Body VLA Behaviors to Scene-Scale Aerial Manipulation