pith. sign in
Pith Number

pith:CLXB2SP2

pith:2024:CLXB2SP2UUUTKFNJPVGOMMGOJK
not attested not anchored not stored refs resolved

CogVLM2: Visual Language Models for Image and Video Understanding

Bin Xu, Da Yin, Debing Liu, Guanyu Feng, Jie Tang, Ji Qi, Juanzi Li, Junhui Ji, Lei Zhao, Ming Ding, Peng Zhang, Qingsong Lv, Shiyu Huang, Weihan Wang, Wenmeng Yu, Wenyi Hong, Xiaohan Zhang, Xiaotao Gu, Xixuan Song, Yan Wang, Yean Cheng, Yuxiao Dong, Zhao Xue, Zhuoyi Yang, Zihan Wang

The CogVLM2 family reaches state-of-the-art results on image and video benchmarks by refining visual expert architectures and training recipes.

arxiv:2408.16500 v1 · 2024-08-29 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CLXB2SP2UUUTKFNJPVGOMMGOJK}

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

CogVLM2 family has achieved state-of-the-art results on benchmarks like MMBench, MM-Vet, TextVQA, MVBench and VCGBench.

C2weakest assumption

That the reported benchmark improvements stem primarily from the described architecture changes and training recipes rather than undisclosed increases in model size, data volume, or compute.

C3one line summary

CogVLM2 family achieves state-of-the-art results on image and video understanding benchmarks through improved visual expert architecture, higher resolution inputs, and automated temporal grounding for videos.

References

94 extracted · 94 resolved · 20 Pith anchors

[1] M. Acharya, K. Kafle, and C. Kanan. Tallyqa: Answering complex counting questions. In Proc. of Association for the Advancement of Artificial Intelligence, 2019 2019
[2] GPT-4 Technical Report 2023 · arXiv:2303.08774
[3] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2010 · arXiv:2010.11929
[4] S. Antol, A. Agrawal, J. Lu, M. Mitchell, D. Batra, C. L. Zitnick, and D. Parikh. Vqa: Visual question answering. In Proc. of International Conference on Computer Vision, pages 2425–2433, 2015 2015
[6] Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023 · arXiv:2308.12966

Formal links

2 machine-checked theorem links

Cited by

33 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:46.728968Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

12ee1d49faa5293515a97d4ce630ce4ab4f212633893fb842a1cdacd5ad6e731

Aliases

arxiv: 2408.16500 · arxiv_version: 2408.16500v1 · doi: 10.48550/arxiv.2408.16500 · pith_short_12: CLXB2SP2UUUT · pith_short_16: CLXB2SP2UUUTKFNJ · pith_short_8: CLXB2SP2
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CLXB2SP2UUUTKFNJPVGOMMGOJK \
  | 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: 12ee1d49faa5293515a97d4ce630ce4ab4f212633893fb842a1cdacd5ad6e731
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "4a0b0561fb635c897f4d823de89ce5cf6644e8c9e66a8d0e0a72614a246a4b9f",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-08-29T12:59:12Z",
    "title_canon_sha256": "9b21e119188e35c13e6672981c4e7ab473790a80b12ce65aa9eb12dddf1a2839"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2408.16500",
    "kind": "arxiv",
    "version": 1
  }
}