pith:NLVIECDO
Skipping the Zeros in Diffusion Models for Sparse Data Generation
Diffusion models can generate sparse data by modeling only non-zero values while handling zero locations separately.
arxiv:2605.01817 v2 · 2026-05-03 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NLVIECDOXB5FZVOD2FTYZJ6XYS}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
With Sparsity-Exploiting Diffusion (SED), we model only non-zero values, preserving sparsity. SED delivers computational savings while maintaining or improving generation quality by skipping zeros during training and inference.
That the sparsity pattern (locations of zeros) is independent of the non-zero values and can be handled separately without losing critical distributional information about the data.
SED modifies diffusion models to generate only non-zero values in sparse data, preserving sparsity patterns, cutting computation, and matching or beating standard DM performance on benchmarks.
Receipt and verification
| First computed | 2026-05-27T01:05:55.829130Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
6aea82086eb87a5cd5c3d1678ca7d7c49326c83e674f0b749b7a0713df93aec5
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NLVIECDOXB5FZVOD2FTYZJ6XYS \
| 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: 6aea82086eb87a5cd5c3d1678ca7d7c49326c83e674f0b749b7a0713df93aec5
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a8d46a7d4c95a6441c9ed13d0970d4453b79cc421f31eff3f953af06934ee603",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-03T10:51:25Z",
"title_canon_sha256": "1dd872630ceb03138578a41ab6e53156a7d63d0b85f58bce000883750c5ff7a2"
},
"schema_version": "1.0",
"source": {
"id": "2605.01817",
"kind": "arxiv",
"version": 2
}
}