← Leaderboard

RFM-1

VLA
Covariant · Mar 11, 2024

8B any-to-any transformer trained on text, images, video, robot actions and physical measurements, aimed at warehouse pick-and-place, with video prediction as a learned physics model. Covariant published no public-benchmark results.

Type
VLA
Parameters
8B
Backbone
Pretrained LLM, trained any-to-any
Weights
Closed
License
–
Commercial use
Unclear
Released
Mar 11, 2024
Robots
warehouse picking arms
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