Skip to content

[Feature Request] Open-source training / fine-tuning scripts for MiniCPM-RobotManip #6

Description

@kiossupersure-lgtm

We are trying to adapt MiniCPM-RobotManip to a new robot arm for a specific manipulation task. The inference side is clear — vla_infer.py exposes the embodiment_id interface and action_head.max_num_embodiments for multi-embodiment support. However, the current repository only includes inference code; no training or fine-tuning scripts are provided for RobotManip.

Questions

  1. Fine-tuning scripts: Is there a plan to open-source the training/fine-tuning code for MiniCPM-RobotManip? Even a minimal script covering data loading, optimizer setup, and checkpoint saving would be very helpful.

  2. New embodiment registration: What is the recommended workflow for adding a new embodiment_id beyond the ones already in the released weights? Does this require retraining from scratch, or is there a fine-tuning path that only updates the action head for the new embodiment?

  3. Data format: Could you document or provide a sample of the training data format expected by RobotManip (state shape, action shape, image resolution, etc.)? The inference script implies STATE_DIM = 80 and action shape (30, 80), but the mapping from real robot joints to this 80-dim space is unclear.

  4. Data quantity guidance: Are there any ablation results or rule-of-thumb recommendations for how many demonstration episodes are needed to fine-tune on a new embodiment/task?

Any pointers — even a rough timeline or a link to an internal script — would be greatly appreciated. Thank you for the great work on this project!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions