← Leaderboard
RFM-1
VLACovariant · 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 benchmarksNo benchmark results recorded yet.
Not reported on 13 benchmarks
Wrong or missing number? Report an error