pith. sign in
Pith Number

pith:AAS5H6WR

pith:2026:AAS5H6WR6BTUJYIRHJ4U7HKY5H
not attested not anchored not stored refs resolved

From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing

Anirudh Sundara Rajan, Krishna Kumar Singh, Yong Jae Lee

Coupling a planner with a reward-driven orchestrator enables reliable multi-step image editing from abstract instructions.

arxiv:2605.15181 v1 · 2026-05-14 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{AAS5H6WR6BTUJYIRHJ4U7HKY5H}

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

By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.

C2weakest assumption

A vision-language judge can reliably provide accurate outcome-based rewards for both instruction adherence and visual quality across diverse editing tasks.

C3one line summary

A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.

References

65 extracted · 65 resolved · 20 Pith anchors

[1] Qwen3-VL Technical Report 2025 · arXiv:2511.21631
[2] In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
[3] In: Proceed- ings of the IEEE/CVF International Conference on Computer Vision 2023
[4] Emerging Properties in Unified Multimodal Pretraining 2025 · arXiv:2505.14683
[5] arXiv preprint arXiv:2309.17102 (2023) 2023

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-17T21:40:25.159506Z
Last reissued 2026-05-17T21:57:18.530785Z
Builder pith-number-builder-2026-05-17-v1
Signature unsigned_v0
Schema pith-number/v1.0

Canonical hash

0025d3fad1f06744e1113a794f9d58e9d3fbcd060b90873e4cad847620f61ffe

Aliases

arxiv: 2605.15181 · arxiv_version: 2605.15181v1 · pith_short_12: AAS5H6WR6BTU · pith_short_16: AAS5H6WR6BTUJYIR · pith_short_8: AAS5H6WR
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H \
  | 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: 0025d3fad1f06744e1113a794f9d58e9d3fbcd060b90873e4cad847620f61ffe
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "9a53781f1c5961e660ff49946a7cb60b048666d463bd426a81f4b0d94f6a8e7e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T17:58:19Z",
    "title_canon_sha256": "bf8f241f814970b333036be9114bc2b37463e1f7f9f87fe4f7bf021354706150"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15181",
    "kind": "arxiv",
    "version": 1
  }
}