RLDX-1.1
Update of RLDX-1 with a refined training corpus, padded-action masking and faster training and inference. The weights are non-commercial, attribution and share-alike; commercial use needs written permission from RLWRLD. Its RoboCasa365 score is self-reported and not on the official board.
RLWRLD · Nov 12, 2026 · VLA · built on RLDX-1Report an error
97.9%LIBERO · #41 of 83
40.2%RoboCasa365 · #17 of 29
6.6BParameters
2Benchmarks reported
Benchmark results2
RoboCasa365Simulation
- Paper / model card ↗Nov 12, 2026· self-reported
#17 of 2940.2%, self-reported by the authors, not a leaderboard entry
- Paper / model card ↗Nov 12, 2026
#41 of 8397.9%, self-reported by the authors, not a leaderboard entry
Not reported on 13 benchmarks
Wrong or missing number? Report an error