pith. sign in
Pith Number

pith:DRRUJNA2

pith:2026:DRRUJNA2MNQ5FTSSRA74WE5PVW
not attested not anchored not stored refs pending

Efficient Adjoint Matching for Fine-tuning Diffusion Models

Dongsoo Shin, Jaemoo Choi, Jaewoong Choi, Jeongwoo Shin, Joonseok Lee, Wei Guo, Yongxin Chen, Yuchen Zhu

By reformulating the stochastic optimal control problem with linear base drift, Efficient Adjoint Matching speeds up reward fine-tuning of diffusion models up to 4x while matching performance.

arxiv:2605.11480 v2 · 2026-05-12 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{DRRUJNA2MNQ5FTSSRA74WE5PVW}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On standard text-to-image reward fine-tuning benchmarks, EAM converges up to 4x faster than AM and matches or surpasses it across various metrics including PickScore, ImageReward, HPSv2.1, CLIPScore and Aesthetics.

C2weakest assumption

That reformulating the SOC problem with linear base drift and modified terminal cost preserves the original alignment objective and solution quality without introducing bias or loss of expressivity.

C3one line summary

EAM speeds up adjoint matching for diffusion model reward fine-tuning by switching to linear base drift, allowing deterministic few-step solvers and closed-form adjoints with up to 4x faster convergence on text-to-image benchmarks.

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-20T00:03:17.800309Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

1c6344b41a6361d2ce52883fcb13afada8e98f83b41346cb3f23dfa2d25d79cf

Aliases

arxiv: 2605.11480 · arxiv_version: 2605.11480v2 · doi: 10.48550/arxiv.2605.11480 · pith_short_12: DRRUJNA2MNQ5 · pith_short_16: DRRUJNA2MNQ5FTSS · pith_short_8: DRRUJNA2
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/DRRUJNA2MNQ5FTSSRA74WE5PVW \
  | 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: 1c6344b41a6361d2ce52883fcb13afada8e98f83b41346cb3f23dfa2d25d79cf
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "ad3fd56b0337e4767d78b763ec3dc90a9f4b8d0ca658ae3e3d0b8a5f7124f420",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T03:55:12Z",
    "title_canon_sha256": "e028ad2b04f7a6bf7c642840e73e0505b7bf462617a717256e69d84b17bbc50d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11480",
    "kind": "arxiv",
    "version": 2
  }
}