Pith Number

pith:5PAHF7TL

pith:2026:5PAHF7TLEYWWSYVPUV2ZLNVO24

not attested not anchored not stored refs resolved

Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance

Guoqiang Liang, Mike Zheng Shou, Yanzhe Chen, Yiqi Lin, Zechen Bai, Ziyun Zeng

Kiwi-Edit achieves state-of-the-art results in controllable video editing by combining instructions with reference images through a new data pipeline and architecture.

arxiv:2603.02175 v4 · 2026-03-02 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5PAHF7TLEYWWSYVPUV2ZLNVO24}

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

Our model achieves significant gains in instruction following and reference fidelity via a progressive multi-stage training curriculum. Extensive experiments demonstrate that our data and architecture establish a new state-of-the-art in controllable video editing.

C2weakest assumption

The image generative models used in the data pipeline produce synthesized reference scaffolds that are high-fidelity and unbiased enough to train a model that generalizes to real user-provided references without introducing artifacts or distribution shifts.

C3one line summary

Kiwi-Edit introduces a scalable pipeline to generate RefVIE dataset and a unified model using learnable queries plus reference features to achieve new state-of-the-art in instruction-and-reference guided video editing.

References

32 extracted · 32 resolved · 0 Pith anchors

[1] - Object identity, attributes (color, shape, material, style), and edit type must be consistent

[2] - Coherent structure, plausible lighting and texture 2025

[3] Object not swapped/added, or a completely unrelated object appears

[4] Object is changed, but looks nothing like the reference image (wrong color, shape, or class)

[5] Object class is correct, but identity details (texture, specific markings, logos) differ significantly from the reference image

Cited by

8 papers in Pith

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing

Aurora: Unified Video Editing with a Tool-Using Agent

StreamingEffect: Real-Time Human-Centric Video Effect Generation

Sound Sparks Motion: Audio and Text Tuning for Video Editing

Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance

Receipt and verification

First computed	2026-05-18T03:09:23.219439Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ebc072fe6b262d6962afa57595b6aed732be15f207cb133df498536b061d0300

Aliases

arxiv: 2603.02175 · arxiv_version: 2603.02175v4 · doi: 10.48550/arxiv.2603.02175 · pith_short_12: 5PAHF7TLEYWW · pith_short_16: 5PAHF7TLEYWWSYVP · pith_short_8: 5PAHF7TL

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/5PAHF7TLEYWWSYVPUV2ZLNVO24 \
  | 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: ebc072fe6b262d6962afa57595b6aed732be15f207cb133df498536b061d0300

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1d4d9c9f52287d7737edd4900dfb6e570d716a7a4a526f3592fcdcb24500696d",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-03-02T18:46:28Z",
    "title_canon_sha256": "e82812b8063cd874a10adc3deb3298719b67b3b54e2993ac6ab820884bcb1180"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.02175",
    "kind": "arxiv",
    "version": 4
  }
}