pith:H3H5HFP6
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
InternVL scales a vision foundation model to 6 billion parameters and progressively aligns it with an LLM on web-scale image-text data to reach state-of-the-art performance on 32 visual-linguistic benchmarks.
arxiv:2312.14238 v3 · 2023-12-21 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{H3H5HFP65P5WUHA5ERRTE6W4TH}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems.
That scaling the vision model to 6 billion parameters and aligning it progressively with web-scale image-text data from various sources will produce generalizable state-of-the-art performance across 32 diverse benchmarks without significant overfitting or data-source biases.
InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.
References
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-18T04:02:53.809045Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
3ecfd395feebfb6a1c1d2463327adc99ff4b060d707ccbf59f6e4e06d4dc0e4e
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/H3H5HFP65P5WUHA5ERRTE6W4TH \
| 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: 3ecfd395feebfb6a1c1d2463327adc99ff4b060d707ccbf59f6e4e06d4dc0e4e
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "7a45ff5ab2ecc0bdc5ca8cf64ddcbda622701f0eef9e49594e9068a99f433a99",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2023-12-21T18:59:31Z",
"title_canon_sha256": "a1ac82f747e2a3587afe40679d605d0e334026956a02cd3c1db6c73412eb7a52"
},
"schema_version": "1.0",
"source": {
"id": "2312.14238",
"kind": "arxiv",
"version": 3
}
}