pith:TIH647K3
ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales.
arxiv:2605.11704 v2 · 2026-05-12 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{TIH647K3IUPW5WXOAVHHOOJ2WV}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
ScaleMoGen achieves state-of-the-art performance, establishing an FID of 0.030 (vs. 0.045 for MoMask) on HumanML3D and a CLIP Score of 0.693 (vs. 0.685 for MoMask++) on the SnapMoGen dataset, while enabling training-free text-guided motion editing.
That quantizing 3D motions into compositional discrete tokens across multiple skeletal-temporal scales strictly preserves the skeletal hierarchy and that bitwise quantization stabilizes optimization for high-detail motions.
ScaleMoGen introduces a scale-wise autoregressive framework that quantizes motions into hierarchical discrete tokens and predicts next-scale maps to achieve SOTA FID 0.030 on HumanML3D and text-guided editing.
Cited by
Receipt and verification
| First computed | 2026-07-22T01:23:57.266373Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV \
| 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: 9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "029f2390748dcfb23e65b4c19efb9e9185375da087e3ae9e37299de78bb30921",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-12T07:58:58Z",
"title_canon_sha256": "82458e8199abdc58887ab37d94cd7d2900ba3287a795e4cca217b7127d298518"
},
"schema_version": "1.0",
"source": {
"id": "2605.11704",
"kind": "arxiv",
"version": 2
}
}