Pith Number

pith:4HJNTCXO

pith:2024:4HJNTCXO2WO2MWAA5L4UQHONPO

not attested not anchored not stored refs resolved

SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Chen Li, Jinguo Zhu, Kun Yi, Lin Song, Sijie Zhao, Xiaohan Ding, Ying Shan, Yixiao Ge, Yuying Ge

SEED-X is a single multimodal model that comprehends arbitrary-sized images and generates at multiple levels of detail.

arxiv:2404.14396 v2 · 2024-04-22 · 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{4HJNTCXO2WO2MWAA5L4UQHONPO}

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

We present a unified and versatile foundation model, namely, SEED-X, which is able to model multi-granularity visual semantics for comprehension and generation tasks.

C2weakest assumption

That integrating arbitrary-size image comprehension and multi-granularity generation will close the gap between current model capabilities and real-world applicability, assuming successful instruction tuning preserves performance without introducing new limitations.

C3one line summary

SEED-X is a unified multimodal foundation model that handles multi-granularity visual semantics for both comprehension and generation across arbitrary image sizes and ratios.

References

76 extracted · 76 resolved · 29 Pith anchors

[1] Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models 2023

[2] MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models 2023 · arXiv:2304.10592

[3] Visual Instruction Tuning 2023 · arXiv:2304.08485

[4] Kosmos-2: Grounding Multimodal Large Language Models to the World 2023 · arXiv:2306.14824

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

Formal links

1 machine-checked theorem link

Cited by

40 papers in Pith

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies

Bernini: Latent Semantic Planning for Video Diffusion

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

CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Receipt and verification

First computed	2026-05-17T23:38:49.883568Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e1d2d98aeed59da65800eaf9481dcd7bb07925b3977e9f4e3f155cb13bd9a37e

Aliases

arxiv: 2404.14396 · arxiv_version: 2404.14396v2 · doi: 10.48550/arxiv.2404.14396 · pith_short_12: 4HJNTCXO2WO2 · pith_short_16: 4HJNTCXO2WO2MWAA · pith_short_8: 4HJNTCXO

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/4HJNTCXO2WO2MWAA5L4UQHONPO \
  | 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: e1d2d98aeed59da65800eaf9481dcd7bb07925b3977e9f4e3f155cb13bd9a37e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9c00008e7c80a94f887a8c3de96e0de64c122983d342180947e64610740221f4",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-04-22T17:56:09Z",
    "title_canon_sha256": "aa793a029a6f4e2269cf1bf47ecffec1d1eae171983b0e7fb6412ef03ddb001a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2404.14396",
    "kind": "arxiv",
    "version": 2
  }
}