NAT VLA 450M is a robot policy built on Liquid AI’s LFM2-VL-450M. It turns images, natural-language instructions and robot state into time-ordered NAT action tokens for streaming control. LeRobot supports fine-tuning and token-prefix real-time chunking.

Overview

Model type
Action policy
Architecture
VLA
Action generation
Autoregressive
Listed versions
NAT VLA 450M

Papers & reports (1)

NAT: Scaling Causal Neural Action Tokenizers Across Embodiments

Paper available

Authors & affiliations (3)

Author order: Original order

  1. Ahad Jawaid

    Not provided

  2. Alexander Swerdlow

    Stanford University

  3. Yu Xiang

    The University of Texas at Dallas

First published
Not provided
Latest paper revision
Not provided
Venue
Not provided

Covered model versions

Paper ↗PDF ↗

Official resources

Submit a source or correction