OpenBMB / OpenBMB/DeepThinkVLA

libero-plus

Open
#4 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
530
Forks
50
PR merge metrics
No merged PRs in 30d

Description

Hello, congratulations to DeepThinkVLA for achieving excellent results on libero-plus. I have some questions to ask about libero-plus.

  1. Do you train a single model for all libero tasks, or do you train a separate model for each task?
  2. Does the training dataset and the inference/test dataset include libero_90?
  3. Which model achieved a score of 79, the SFT model or the RL model?
  4. What are your insights on this excellent result? Where does it come from?
    Looking forward to your communication, thank you.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue asks four questions about libero-plus, including training setup, dataset coverage, model scores, and the source of the result. No files, tests, or entry points are named; completion would require obtaining and documenting answers from the project maintainers.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.