RoboUniView

Reported on 2 benchmarks across 2 tasks · 1 paper · 2 SOTA

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)· 2024-06-27
3.855
best: 4.44 (DreamVLA)
SOTA
RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation arXiv:2406.18977

Methodology1 result

Zero-shot GeneralizationonCALVIN
Avg. sequence length· 2024-06-27
3.647
best: 4.04 (GR-MG)
SOTA
RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation arXiv:2406.18977