pith:EIGDAX7Z
Structured State-Space Regularization for Generation-Friendly Image Tokenization
A regularizer that makes image tokenizers mimic state-space model dynamics produces more compact and generation-friendly latent spaces.
arxiv:2604.11089 v2 · 2026-04-13 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{EIGDAX7ZAOHEVH2KQQWXCK73O7}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
our regularizer enforces encoding of fine spatial structures and frequency-domain cues into compact latent features; leading to more effective use of representation capacity and improved generative modelability.
That guiding tokenizers to mimic SSM hidden-state dynamics will reliably transfer frequency awareness and spatial structure encoding to image latents without introducing new artifacts or requiring dataset-specific tuning.
A new regularizer transfers frequency awareness from state-space models into image tokenizers, yielding more compact latents that improve diffusion-model generation quality with little reconstruction penalty.
Receipt and verification
| First computed | 2026-05-20T01:05:13.067756Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
220c305ff9038e4a9f4a842d712bfb77eb3e9edf6150677c7e0e6ea7e109d615
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/EIGDAX7ZAOHEVH2KQQWXCK73O7 \
| 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: 220c305ff9038e4a9f4a842d712bfb77eb3e9edf6150677c7e0e6ea7e109d615
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "affd9c1adb937ede198834de00c281eeddbf84eac2bb985b7cd204689a91efcb",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-13T07:10:17Z",
"title_canon_sha256": "97cdcc31809b4718c0602228f145457dd9a18e6cd75c57ab72212c38dfd497d3"
},
"schema_version": "1.0",
"source": {
"id": "2604.11089",
"kind": "arxiv",
"version": 2
}
}