← Leaderboard

Fast-in-Slow (FiS-VLA)

VLA
Peking University · Jun 2, 2025

Dual-system VLA from PKU with AI² Robotics, BAAI and CUHK that embeds a fast action module inside the slow VLM. Results are self-reported (68% on the authors’ AgileX tasks vs 59% for π0; 69% on RLBench).

Type
VLA
Parameters
7B
Backbone
Prismatic (LLaMA-2 7B)
Weights
Open
License
MIT
Commercial use
Allowed
Released
Jun 2, 2025
Robots
AgileX dual-arm
SO-101
–
LeRobot
–
Inputs
–
VRAM
–

Benchmark results

0 of 13 benchmarks

No benchmark results recorded yet.

Not reported on 13 benchmarks
Wrong or missing number? Report an error