kaiwen22026MIT

RoboMME no-VQA Stage-A baseline checkpoints

Final converged checkpoints for the no-VQA Stage-A baseline ablation of RoboMME, including models for place, height, hvlv, and contact tasks with configuration and dataset statistics.

Downloads38

Why This Matters for Physical AI

These baseline checkpoints enable reproducible evaluation and ablation studies on multimodal robotic learning without visual question-answering components.

Technical Profile

Task Types
placeheighthvlvcontact
Data Format
PyTorch
License
MIT
Part of the RoboMME family

Access

Need custom physical AI data?

Claru builds purpose-built datasets for any environment applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets