RoboLLM (VIT-B)

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

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

Computer Vision2 results

Instance SegmentationonARMBench
AP50· 2023-10-16
82
best: 86.37 (RISE (VIT-B))
SOTA
RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models arXiv:2310.10221
Instance SegmentationonARMBench
AP75· 2023-10-16
74
best: 77.51 (RISE (VIT-B))
SOTA
RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models arXiv:2310.10221