Pith Number

pith:NOE5TNB5

pith:2025:NOE5TNB5M3JEXV2H2SFPTBCYBU

not attested not anchored not stored refs resolved

Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation

Chao Liao, Jie Wu, Liang Li, Liyang Liu, Weilin Huang, Wenliang Zhao, Xinyu Zhang, Xun Wang, Zhengxiong Luo, Zhi Tian

Mogao is a single model that generates arbitrary sequences mixing text and images by fusing autoregressive and diffusion components.

arxiv:2505.05472 v2 · 2025-05-08 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{NOE5TNB5M3JEXV2H2SFPTBCYBU}

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

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

Mogao not only achieves state-of-the-art performance in multi-modal understanding and text-to-image generation, but also excels in producing high-quality, coherent interleaved outputs. Its emergent capabilities in zero-shot image editing and compositional generation highlight Mogao as a practical omni-modal foundation model.

C2weakest assumption

The key technical improvements (deep-fusion design, dual vision encoders, interleaved rotary position embeddings, and multi-modal classifier-free guidance) successfully combine the strengths of autoregressive text models and diffusion image models for arbitrary interleaved sequences.

C3one line summary

Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.

References

99 extracted · 99 resolved · 37 Pith anchors

[1] Pixtral 12b.arXiv preprint arXiv:2410.07073, 2024 2024 · arXiv:2410.07073

[2] Flamingo: a visual language model for few-shot learning 2022

[3] Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023 · arXiv:2308.12966

[4] Qwen2.5-VL Technical Report 2025 · arXiv:2502.13923

[5] Improving image generation with better captions.Computer Science 2023

Formal links

3 machine-checked theorem links

Cited by

18 papers in Pith

OmniGen2: Towards Instruction-Aligned Multimodal Generation

DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation

PixelGen: Improving Pixel Diffusion with Perceptual Supervision

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

HunyuanImage 3.0 Technical Report

Receipt and verification

First computed	2026-05-17T23:38:14.723810Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6b89d9b43d66d24bd747d48af984580d2c2450ff9b113ef15376397d8b9489be

Aliases

arxiv: 2505.05472 · arxiv_version: 2505.05472v2 · doi: 10.48550/arxiv.2505.05472 · pith_short_12: NOE5TNB5M3JE · pith_short_16: NOE5TNB5M3JEXV2H · pith_short_8: NOE5TNB5

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/NOE5TNB5M3JEXV2H2SFPTBCYBU \
  | 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: 6b89d9b43d66d24bd747d48af984580d2c2450ff9b113ef15376397d8b9489be

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "37ebe6436300552155727322e1e80dae910b976364d4b35c782a49b466a7c6a3",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-05-08T17:58:57Z",
    "title_canon_sha256": "2901d2f3db0f233e2de4c877ae6dbb6888068a827bb4c6b701deff4db654f564"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.05472",
    "kind": "arxiv",
    "version": 2
  }
}