pith:UMTFWY7F
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
By aligning images and videos into the language feature space before projection, a single LLM processes both modalities and lets them improve each other.
arxiv:2311.10122 v3 · 2023-11-16 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UMTFWY7FF7LPB4AG4LC3PPN4NN}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
we unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM. As a result, we establish a simple but robust LVLM baseline, Video-LLaVA, which learns from a mixed dataset of images and videos, mutually enhancing each other.
due to the lack of unified tokenization for images and videos, namely misalignment before projection, it becomes challenging for a Large Language Model (LLM) to learn multi-modal interactions from several poor projection layers.
Video-LLaVA creates a unified visual representation for images and videos via pre-projection alignment, enabling mutual enhancement from joint training and strong results on image and video benchmarks.
References
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-17T23:39:22.231807Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
a3265b63e52fd6f0f006e2c5b7bdbc6b59ff9c3187e6dd8a99d4b5d12ca0d596
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UMTFWY7FF7LPB4AG4LC3PPN4NN \
| 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: a3265b63e52fd6f0f006e2c5b7bdbc6b59ff9c3187e6dd8a99d4b5d12ca0d596
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "c80295a5762ecdeb6e65c5f49691842dea7b0fe27da82d7476d300d10c866324",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2023-11-16T10:59:44Z",
"title_canon_sha256": "169b24f471d2208db1ce36173b5691902e0fd44518285d76760c7236864b0685"
},
"schema_version": "1.0",
"source": {
"id": "2311.10122",
"kind": "arxiv",
"version": 3
}
}