Meta Motivo study
Meta Motivo human-likeness preference study
Fifty raters compared videos of two simulated-humanoid policies on 95 tasks for task success and human-likeness.1
Last checked 10 Oct 2026Basic entry11 of 16 facts checked at the sourceNext check 8 Apr 2027
Runs in
Simulation2
Checked against real robots
Not checked
Skill
Moving like people
Robot
Game character1
Licence
Unclear3
Comparisons with real robots
Not checked1
Details
Body is a simulated SMPL humanoid character in MuJoCo; no physical counterpart and no real-robot experiment in the paper.
Details
About
- What it is
- In-house test Inferred2
More
Classified by the Atlas from how the authors describe and distribute it.
- Built by
- FAIR at Meta; one author at Mila/McGill (work done at Meta), one at FAIR and UCL.1
- Released
- 2024-12-12 (Meta research publication page).4
- Version
- arXiv v1; code release tags v0.1.0-v0.1.2 (latest 2025-01-27).5
- Last update
- No change to the study after arXiv v1 (2025-04-15). Code repo last push 2025-06-10 (bug fix).5
Setup
Scoring and access
Sources 5
- 1Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models (full text)Paper · Apr 2025 · checked 10 Oct 2026
- 2Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation ModelsPaper · Apr 2025 · checked 10 Oct 2026
- 3facebookresearch/metamotivo on GitHub (blob)Repository · checked 10 Oct 2026
- 4Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models | Research - AI at MetaOfficial blog · checked 10 Oct 2026
- 5facebookresearch/metamotivo on GitHub (repository)Repository · checked 10 Oct 2026
Change history
- Created as a basic entry: identity facts checked at primary sources (phase 1 re-verification).