Pith Number

pith:OGXGRTKC

pith:2023:OGXGRTKCWZTF6E46FCQUPHGSCH

not attested not anchored not stored refs resolved

InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition

Bin Wang, Chao Xu, Conghui He, Dahua Lin, Hang Yan, Haodong Duan, Jiaqi Wang, Jingwen Li, Kai Chen, Linke Ouyang, Pan Zhang, Shuangrui Ding, Songyang Zhang, Wei Li, Wenwei Zhang, Xiaoyi Dong, Xingcheng Zhang, Xinyue Zhang, Yuhang Cao, Yu Qiao, Zhiyuan Zhao

InternLM-XComposer generates articles with automatically inserted context-appropriate images while achieving state-of-the-art results on vision-language benchmarks.

arxiv:2309.15112 v5 · 2023-09-26 · cs.CV

Open paper page JSON What is a Pith Number?

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

Claims

C1strongest claim

Our model consistently achieves state-of-the-art results across various mainstream benchmarks for vision-language foundational models, including MME Benchmark, MMBench, MMBench-CN, Seed-Bench, CCBench, QBench and Tiny LVLM.

C2weakest assumption

That the custom human-plus-GPT-4V evaluation procedure for text-image composition reliably measures quality and that the training data strategies produce genuine comprehension rather than benchmark overfitting.

C3one line summary

InternLM-XComposer generates articles with seamlessly integrated images and achieves state-of-the-art results on vision-language benchmarks including MME, MMBench, and Seed-Bench.

References

119 extracted · 119 resolved · 10 Pith anchors

[1] Flamingo: a visual language model for few-shot learning,

[2] Lawrence Zitnick, and Devi Parikh 2015

[3] Openflamingo: An open- source framework for training large autoregressive vision- language models 2023

[4] Qwen-vl: A frontier large vision-language model with versatile abilities 2023

[5] Baichuan 2: Open large-scale language models 2023

Cited by

17 papers in Pith

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

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

InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

Receipt and verification

First computed	2026-05-17T23:38:13.920003Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

71ae68cd42b6665f139e28a1479cd211e56ebd782f3efa8b38a36b487ce38b84

Aliases

arxiv: 2309.15112 · arxiv_version: 2309.15112v5 · doi: 10.48550/arxiv.2309.15112

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/OGXGRTKCWZTF6E46FCQUPHGSCH \
  | 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: 71ae68cd42b6665f139e28a1479cd211e56ebd782f3efa8b38a36b487ce38b84

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6fd5a608d0dbd3dbb100cb2814ac5a6c4638bdffe3cc60835e63055b9deb6d06",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-09-26T17:58:20Z",
    "title_canon_sha256": "eda8b0b16f0169266a3c74c46c739ab855ef48ca4e4863a8abf7e26df1a59fc5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2309.15112",
    "kind": "arxiv",
    "version": 5
  }
}