pith:BGHEEHJA
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
A one-step block diffusion model generates clinically accurate chest X-ray reports eight times faster than autoregressive methods by distilling joint token dependencies.
arxiv:2604.09450 v2 · 2026-04-10 · cs.LG · cs.AI · eess.IV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{BGHEEHJASENPYOMFSTPNI2DRYV}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
ECHO surpasses state-of-the-art autoregressive methods, improving RaTE and SemScore by 64.33% and 60.58% respectively, while achieving an 8× inference speedup without compromising clinical accuracy.
That the Direct Conditional Distillation framework successfully encodes joint token dependencies from on-policy trajectories to overcome mean-field bias in one-step generation, without introducing new coherence failures not captured by the reported metrics.
ECHO is a one-step block diffusion VLM for chest X-ray reports that improves RaTE and SemScore by over 60% while delivering 8x faster inference than autoregressive baselines.
Cited by
Receipt and verification
| First computed | 2026-05-20T00:04:31.208955Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
098e421d20911afc398594ded46871c55d5f5558e0651f9786c464ba0100cfb6
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV \
| 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: 098e421d20911afc398594ded46871c55d5f5558e0651f9786c464ba0100cfb6
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "689ae9778f9f72a1df5c06ff46733e928ce5dc0c1d874f7c4852dca7abcfb449",
"cross_cats_sorted": [
"cs.AI",
"eess.IV"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-10T16:07:14Z",
"title_canon_sha256": "b2af0b2c94d7ddaf1f807a8ba8fba25bf1d35880301fe0a175e7c792bb2b7b7d"
},
"schema_version": "1.0",
"source": {
"id": "2604.09450",
"kind": "arxiv",
"version": 2
}
}