Pith Number

pith:A5YWT5NP

pith:2025:A5YWT5NPNYXLFFO6RCZBDF3ZZW

not attested not anchored not stored refs resolved

MMaDA: Multimodal Large Diffusion Language Models

Bowen Li, Ke Shen, Ling Yang, Mengdi Wang, Xinchen Zhang, Ye Tian, Yunhai Tong

A single diffusion architecture unifies text reasoning, multimodal understanding, and image generation without modality-specific parts.

arxiv:2505.15809 v2 · 2025-05-21 · 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{A5YWT5NPNYXLFFO6RCZBDF3ZZW}

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

MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation.

C2weakest assumption

The shared probabilistic formulation and modality-agnostic design in the unified diffusion architecture is sufficient to seamlessly integrate and process different data types without modality-specific components.

C3one line summary

MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks.

References

126 extracted · 126 resolved · 32 Pith anchors

[1] Improving language understanding by generative pre-training 2018

[2] Language models are few-shot learners 2020

[3] OpenAI o1 System Card 2024 · arXiv:2412.16720

[5] Vl-gpt: A generative pre-trained transformer for vision and language understanding and generation 2023

[6] Emu: Generative Pretraining in Multimodality 2023 · arXiv:2307.05222

Formal links

2 machine-checked theorem links

Cited by

31 papers in Pith

Improving Sampling for Masked Diffusion Models via Information Gain

Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving

TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers

Receipt and verification

First computed	2026-05-17T23:38:52.311878Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

077169f5af6e2eb295de88b2119779cd86902265d8155d7d249a5cdc30022e2e

Aliases

arxiv: 2505.15809 · arxiv_version: 2505.15809v2 · doi: 10.48550/arxiv.2505.15809 · pith_short_12: A5YWT5NPNYXL · pith_short_16: A5YWT5NPNYXLFFO6 · pith_short_8: A5YWT5NP

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/A5YWT5NPNYXLFFO6RCZBDF3ZZW \
  | 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: 077169f5af6e2eb295de88b2119779cd86902265d8155d7d249a5cdc30022e2e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9915f21e3ed164bef883cebc22d229638a7cf8d206b66e5fa1e279444700fc8d",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-05-21T17:59:05Z",
    "title_canon_sha256": "9c0d94bf569c6f3f39389aa289310f824ba48a152bb9e854e82bacb938cf3058"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.15809",
    "kind": "arxiv",
    "version": 2
  }
}