pith:IOVTADSA
Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
Many reward-based fine-tuning methods for diffusion and flow models reduce to a single score-matching objective against a value-guided target.
arxiv:2604.17415 v3 · 2026-04-19 · cs.LG · cs.AI · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{IOVTADSAIQNRQIZOM5ICML5RTE}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Although existing methods are derived from different perspectives, we show that many can be written under a common framework, which we call reward score matching (RSM).
That the primary distinctions among existing methods reduce to the construction of the value-guidance estimator and the effective optimization strength across timesteps, without material loss of generality or overlooked auxiliary mechanisms.
Reward Score Matching unifies reward-based fine-tuning for flow and diffusion models by recasting alignment as score matching to a value-guided target.
Cited by
Receipt and verification
| First computed | 2026-06-02T01:03:47.239586Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
43ab300e40441b18232e6750262fb19903d11d9b06c5390de10b5769fee83e8f
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/IOVTADSAIQNRQIZOM5ICML5RTE \
| 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: 43ab300e40441b18232e6750262fb19903d11d9b06c5390de10b5769fee83e8f
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "965112703ecf90a21ea7fa74bb4649f763107130cbece4ac12a9ddcc00b3251d",
"cross_cats_sorted": [
"cs.AI",
"cs.CV"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-19T12:47:52Z",
"title_canon_sha256": "a9b9c9999d2b319856cd98f141b6c5316e3159c1ff90fcf1fc01e0069613e15f"
},
"schema_version": "1.0",
"source": {
"id": "2604.17415",
"kind": "arxiv",
"version": 3
}
}