Pith Number

pith:ID7PWW53

pith:2023:ID7PWW53VUCANRI32L4VIQM256

not attested not anchored not stored refs resolved

Emu: Generative Pretraining in Multimodality

Fan Zhang, Hongcheng Gao, Jingjing Liu, Qiying Yu, Quan Sun, Tiejun Huang, Xiaosong Zhang, Xinlong Wang, Yueze Wang, Yufeng Cui

A single Transformer model generates images and text by autoregressively predicting the next token or visual embedding from interleaved inputs.

arxiv:2307.05222 v2 · 2023-07-11 · 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{ID7PWW53VUCANRI32L4VIQM256}

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

Across a broad range of zero-shot/few-shot tasks including image captioning, visual question answering, video question answering and text-to-image generation, Emu demonstrates superb performance compared to state-of-the-art large multimodal models.

C2weakest assumption

That encoding visual signals into embeddings and training with a unified next-token or next-embedding objective will produce coherent multimodal generation without modality-specific losses or architectures.

C3one line summary

Emu is a multimodal foundation model that unifies image and text generation via autoregressive pretraining on interleaved multimodal data, showing strong zero-shot performance on captioning, VQA, and text-to-image tasks.

References

22 extracted · 22 resolved · 0 Pith anchors

[1] and contains large-scale image-text pairs data. LAION-COCO (lai, b) is captioned 600M images from LAION-2B with an ensemble of BLIP (Li et al., 2022) and CLIP (Radford et al., 2021) models. Whereas th 2022

[2] Make sure to check the weather forecast before your visit and pack appropriate clothing and gear

[3] Make sure to stay on designated trails and keep your distance from any wildlife you encounter

[4] Make sure to check with local authorities before swimming or boating in the lake to ensure it is safe to do so

[5] Make sure to familiarize yourself with the lake's layout and any potential hazards before venturing out on the water

Formal links

2 machine-checked theorem links

Cited by

23 papers in Pith

Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems

NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Receipt and verification

First computed	2026-05-17T23:38:46.700545Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

40fefb5bbbad0406c51bd2f954419aefbb8537aa8f92f967a5d8353a016028c6

Aliases

arxiv: 2307.05222 · arxiv_version: 2307.05222v2 · doi: 10.48550/arxiv.2307.05222 · pith_short_12: ID7PWW53VUCA · pith_short_16: ID7PWW53VUCANRI3 · pith_short_8: ID7PWW53

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/ID7PWW53VUCANRI32L4VIQM256 \
  | 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: 40fefb5bbbad0406c51bd2f954419aefbb8537aa8f92f967a5d8353a016028c6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "46600ae81117b6ccc061a48ecab7a9f32c222fa5a904f09d6e372d0982f5c569",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-07-11T12:45:39Z",
    "title_canon_sha256": "0bc9d5de0efbc6d14eda4e338377e6441a0a00c832fa1e567e5af7edca242882"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2307.05222",
    "kind": "arxiv",
    "version": 2
  }
}