pith:POKFP6OC
Language Modeling with Hyperspherical Flows
S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks.
arxiv:2605.11125 v2 · 2026-05-11 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{POKFP6OCYOCQ64NHNEJG7AT25X}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
S-FLM substantially improves continuous flow language models on large-vocabulary reasoning and closes the gap to masked diffusion under standard-temperature sampling (T=1), while a gap remains under optimized low-temperature (T=0.1) decoding.
That rotating vectors on the hypersphere along a learned velocity field provides a semantically meaningful transport from noise to data, unlike the equidistant one-hot vectors used in prior FLMs.
S-FLM rotates vectors on a hypersphere using a learned velocity field to generate language sequences, improving continuous flow models on large-vocabulary reasoning and closing the gap to masked diffusion at standard sampling temperature.
Formal links
Receipt and verification
| First computed | 2026-05-20T00:03:17.323579Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
7b9457f9c2c3850f71a769126f827aedfad77e473242884f12d147b28b150667
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X \
| 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: 7b9457f9c2c3850f71a769126f827aedfad77e473242884f12d147b28b150667
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "4c1d93b0ab4c07bab89bfb895a6b1534d3b13139c60811c54c05609dda45629f",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-11T18:32:32Z",
"title_canon_sha256": "7dd277264b8017cb3edc7f4dd13a76827cf243306fcffe9f01e74e7f84281b48"
},
"schema_version": "1.0",
"source": {
"id": "2605.11125",
"kind": "arxiv",
"version": 2
}
}