pith:VRNYWBAP
Vero: An Open RL Recipe for General Visual Reasoning
Open reinforcement learning with broad visual data builds general reasoners that rival closed models.
arxiv:2604.04917 v3 · 2026-04-06 · cs.CV · cs.AI · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{VRNYWBAP4OGGSTHSNUUWSTB2UH}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Vero achieves state-of-the-art performance, improving over four base models by 3.6-5.3 points on average across VeroEval, our suite of 30 challenging benchmarks. Starting from Qwen3-VL-8B-Instruct, Vero outperforms Qwen3-VL-8B-Thinking on 23 of 30 benchmarks without additional proprietary thinking data.
That the observed gains are primarily driven by broad data coverage and task-routed rewards rather than other unstated factors such as training hyperparameters, base model choice, or evaluation contamination; the abstract provides no controls or ablations to isolate these effects.
Vero is an open VLM family trained via RL on Vero-600K (600K samples from 59 datasets across six categories) with task-routed rewards, achieving SOTA gains of 3.6-5.3 points on 30 visual reasoning benchmarks.
Formal links
Receipt and verification
| First computed | 2026-06-19T16:12:53.850107Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
ac5b8b040fe38c694cf26d29694c3aa1c040180d3d5e4a74933df1554b7f149f
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/VRNYWBAP4OGGSTHSNUUWSTB2UH \
| 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: ac5b8b040fe38c694cf26d29694c3aa1c040180d3d5e4a74933df1554b7f149f
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "02f3aeeaf574c5c19b0719a3eda8ffe161688a6249952d286b9a3b739270eeeb",
"cross_cats_sorted": [
"cs.AI",
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-06T17:56:25Z",
"title_canon_sha256": "b239fcf64cf625c6e1202214cd9c444a5428698b2729a6af594559fb0672bc09"
},
"schema_version": "1.0",
"source": {
"id": "2604.04917",
"kind": "arxiv",
"version": 3
}
}