Pith Number

pith:YBWMYB6X

pith:2026:YBWMYB6XSOOZE2I3FLDL6CKLF6

not attested not anchored not stored refs resolved

Qwen-Image-VAE-2.0 Technical Report

Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng, Lihan Jiang, Lin Qu, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoxiao Xu, Xiao Xu, Xiaoyue Chen, Yanran Zhang, Yan Shu, Yilei Chen, Yiliang Gu, Yi Wang, Yixian Xu, Yujia Wu, Yu Wu, Yuxiang Chen, Zekai Zhang, Zhendong Wang, Zihao Liu, Zikai Zhou

Qwen-Image-VAE-2.0 delivers state-of-the-art image reconstruction at high compression ratios while accelerating diffusion model convergence.

arxiv:2605.13565 v1 · 2026-05-13 · 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{YBWMYB6XSOOZE2I3FLDL6CKLF6}

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

Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines.

C2weakest assumption

The assumption that scaling training to billions of images combined with synthetic rendering and semantic alignment will produce a high-dimensional latent space that is highly amenable to diffusion modeling without introducing new artifacts or domain biases.

C3one line summary

Qwen-Image-VAE-2.0 achieves state-of-the-art high-compression image reconstruction and superior diffusability for diffusion models, with a new text-rich document benchmark.

References

19 extracted · 19 resolved · 14 Pith anchors

[1] Cosmos World Foundation Model Platform for Physical AI · arXiv:2501.03575

[2] Perception Encoder: The best visual embeddings are not at the output of the network · arXiv:2504.13181

[3] HunyuanImage 3.0 Technical Report · arXiv:2509.23951

[4] PaddleOCR 3.0 Technical Report · arXiv:2507.05595

[5] Seedream 3.0 Technical Report · arXiv:2504.11346

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:23.462470Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c06ccc07d7939d92691b2ac6bf094b2fb5c6f6cc8f02e86643fc53da549e7e15

Aliases

arxiv: 2605.13565 · arxiv_version: 2605.13565v1 · doi: 10.48550/arxiv.2605.13565 · pith_short_12: YBWMYB6XSOOZ · pith_short_16: YBWMYB6XSOOZE2I3 · pith_short_8: YBWMYB6X

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/YBWMYB6XSOOZE2I3FLDL6CKLF6 \
  | 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: c06ccc07d7939d92691b2ac6bf094b2fb5c6f6cc8f02e86643fc53da549e7e15

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f6e24bde400885c0d6579e6b385077eafcf9f8777a2da89fc92cac9f31f64458",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T14:04:56Z",
    "title_canon_sha256": "829e1750ce48e2abaeb7fa068dc357e111dd807843d69c81a6abf30dbd1daa1d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13565",
    "kind": "arxiv",
    "version": 1
  }
}