MoDE

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots1 result

Robot ManipulationonCALVIN
avg. sequence length (D to D)· 2024-12-17
4.01
best: 4.44 (DreamVLA)
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning arXiv:2412.12953

Methodology1 result

Zero-shot GeneralizationonCALVIN
Avg. sequence length· uses extra data· 2024-12-17
4.01
best: 4.04 (GR-MG)
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning arXiv:2412.12953