Pith Number

pith:VI6JI2JP

pith:2026:VI6JI2JPS3AKUSROFC5FNYAH27

not attested not anchored not stored refs resolved

Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing

Bo Zheng, Houqiang Li, Litong Gong, Shaodong Xu, Tiezheng Ge, Wengang Zhou, Zexian Li, Zhendong Wang

Edit-GRPO decouples editing and preservation objectives with region-specific signals to keep image edits localized.

arxiv:2605.16951 v1 · 2026-05-16 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VI6JI2JPS3AKUSROFC5FNYAH27}

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

Extensive experiments across diverse image editing scenarios demonstrate that Edit-GRPO significantly improves locality preservation while maintaining strong editing performance compared to existing optimization-based methods.

C2weakest assumption

The assumption that decoupling editing and preservation objectives through region-specific optimization signals will align policy updates with the spatial structure of editing tasks without requiring additional mechanisms to handle boundary effects or context interactions.

C3one line summary

Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.

References

48 extracted · 48 resolved · 25 Pith anchors

[1] Humanedit: A high-quality human-rewarded dataset for instruction-based image editing 2024

[2] Qwen3-VL Technical Report 2025 · arXiv:2511.21631

[3] Training Diffusion Models with Reinforcement Learning 2023 · arXiv:2305.13301

[4] In- structpix2pix: Learning to follow image editing instructions 2022

[5] HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer 2025 · arXiv:2505.22705

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:32.592975Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

aa3c94692f96c0aa4a2e28ba56e007d7f4b3177405ecfe93ebc9f763312b431e

Aliases

arxiv: 2605.16951 · arxiv_version: 2605.16951v1 · doi: 10.48550/arxiv.2605.16951 · pith_short_12: VI6JI2JPS3AK · pith_short_16: VI6JI2JPS3AKUSRO · pith_short_8: VI6JI2JP

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/VI6JI2JPS3AKUSROFC5FNYAH27 \
  | 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: aa3c94692f96c0aa4a2e28ba56e007d7f4b3177405ecfe93ebc9f763312b431e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a3a3fef087b364a0a13849bee6852f2fadf9179bc870efef8a1f7609b4cbeecb",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T12:05:39Z",
    "title_canon_sha256": "bedc4be446d9348cd5880d113743dc3f2714a9637aa9807b855e03c98a613cdf"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16951",
    "kind": "arxiv",
    "version": 1
  }
}