pith:WFARVYX4
DreamGen: Unlocking Generalization in Robot Learning through Video World Models
A simple pipeline adapts video world models to generate synthetic robot trajectories that let humanoid policies generalize to 22 new behaviors and unseen environments from data of a single task.
arxiv:2505.12705 v2 · 2025-05-19 · cs.RO · cs.AI · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{WFARVYX43DK65L5SXE356SZTPU}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Despite its simplicity, DreamGen unlocks strong behavior and environment generalization: a humanoid robot can perform 22 new behaviors in both seen and unseen environments, while requiring teleoperation data from only a single pick-and-place task in one environment.
That the adapted video world models produce sufficiently realistic and embodiment-consistent synthetic videos such that pseudo-actions recovered by the latent action model or IDM yield policies that transfer effectively to the physical robot without large domain gaps.
DreamGen trains robot policies on synthetic trajectories from adapted video world models, enabling a humanoid robot to perform 22 new behaviors in seen and unseen environments from a single pick-and-place teleoperation dataset.
References
Cited by
Receipt and verification
| First computed | 2026-05-17T23:38:49.710381Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
b1411ae2fcd8d5eeafb2b937df4b337d148e5fe34b9c713873d7a41e79330ddc
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/WFARVYX43DK65L5SXE356SZTPU \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: b1411ae2fcd8d5eeafb2b937df4b337d148e5fe34b9c713873d7a41e79330ddc
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "15a1b058cf62eeef9be0ed98732a07113d59ff33a5cc79dbaa3dedc0b1aa0611",
"cross_cats_sorted": [
"cs.AI",
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.RO",
"submitted_at": "2025-05-19T04:55:39Z",
"title_canon_sha256": "5fe7036366dfadbec2fee4d738e16acb05606dedf41aa685db9c3b9c1a71ed51"
},
"schema_version": "1.0",
"source": {
"id": "2505.12705",
"kind": "arxiv",
"version": 2
}
}