pith:IUBQOMLS
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
Medical vision-language models internalize clinical intuition by evolving latent diagnostic memories in their hidden states.
arxiv:2604.26283 v2 · 2026-04-29 · cs.CV · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{IUBQOMLSCECJM5OMKFQ7XAHG33}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
ours, by transferring external expertise into endogenous parameters, significantly outperforms existing state-of-the-art methods, particularly chain-of-thought paradigms, in diagnostic accuracy.
That reinforcement learning with region-level feature masking and full-vocabulary divergence alignment can accurately quantify causal contributions of memories and internalize clinical intuition without introducing artifacts or biases.
MedSynapse-V evolves latent diagnostic memories via meta queries, causal counterfactual refinement with RL, and dual-branch memory transition to outperform prior medical VLM methods in diagnostic accuracy.
Cited by
Receipt and verification
| First computed | 2026-05-20T00:03:12.747641Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
450307317211049675cc5161fb80e6ded9e67f9211f1ba0319e21e26a4397edd
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/IUBQOMLSCECJM5OMKFQ7XAHG33 \
| 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: 450307317211049675cc5161fb80e6ded9e67f9211f1ba0319e21e26a4397edd
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "05489131487f61584c70edb3a5346392f4b7eca887fa3fb64391740bc639e8a4",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-29T04:23:35Z",
"title_canon_sha256": "a7c7e745888dee1f6b543aff740ba8690ae1f7597f204fd7cf4a21afa4308006"
},
"schema_version": "1.0",
"source": {
"id": "2604.26283",
"kind": "arxiv",
"version": 2
}
}