Pith Number

pith:Z7J6R26O

pith:2026:Z7J6R26O2WMKTIDAPIVAZTPWWO

not attested not anchored not stored refs pending

Let ViT Speak: Generative Language-Image Pre-training

Mengcheng Lan, Qi She, Weixian Lei, Yan Fang, Yao Zhao, Yingchen Yu, Yujie Zhong, Yunchao Wei, Yunqing Zhao, Zilong Huang

A ViT can learn to generate language tokens from visual tokens using only a language modeling objective, aligning it with autoregressive LLMs without contrastive batches or a separate text decoder.

arxiv:2605.00809 v2 · 2026-05-01 · 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{Z7J6R26O2WMKTIDAPIVAZTPWWO}

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

Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding.

C2weakest assumption

That training a ViT to predict language tokens directly from visual tokens using only a language modeling objective will produce a vision encoder that aligns effectively with autoregressive LLMs without needing contrastive batch construction or an additional text decoder.

C3one line summary

GenLIP pretrains ViTs to generate language tokens from visual tokens via autoregressive language modeling, matching strong baselines on multimodal tasks with less data.

Receipt and verification

First computed	2026-06-10T01:10:02.635414Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cfd3e8ebced598a9a0607a2a0ccdf6b3880c85160ddfe080754e7dfd7ec6e7ba

Aliases

arxiv: 2605.00809 · arxiv_version: 2605.00809v2 · doi: 10.48550/arxiv.2605.00809 · pith_short_12: Z7J6R26O2WMK · pith_short_16: Z7J6R26O2WMKTIDA · pith_short_8: Z7J6R26O

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/Z7J6R26O2WMKTIDAPIVAZTPWWO \
  | 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: cfd3e8ebced598a9a0607a2a0ccdf6b3880c85160ddfe080754e7dfd7ec6e7ba

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fab2a47d18f8a0fe7e8c6b249310094018ee16cca82076d63b06ce86bd610cfd",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-01T17:51:38Z",
    "title_canon_sha256": "928e2a93b338332a1a6ae9c2c6c6ad21678f39ee6c7230cefc2936ba17eeb327"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.00809",
    "kind": "arxiv",
    "version": 2
  }
}