---
type: "post"
id: "beats-supervised-biomedclip-and-chexagent-baselines-on-mimic-1a7014"
slug: "beats-supervised-biomedclip-and-chexagent-baselines-on-mimic-1a7014"
title: "Beats supervised, BiomedCLIP, and CheXagent baselines on MIMIC-CXR, CheXpert, and PadChest."
description: "A revised paper, “Structure is Supervision: Multiview Masked Autoencoders for Radiology,” describes MVMAE, a self-supervised pretraining framework for radiology studies with multiple image views."
retrieval_nugget: "A revised paper, “Structure is Supervision: Multiview Masked Autoencoders for Radiology,” describes MVMAE, a self-supervised pretraining framework for radiology studies with multiple image views."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["multimodal","models"]
entities: ["MVMAE","MVMAE-V2T","MIMIC-CXR","CheXpert","PadChest","BiomedCLIP","CheXagent"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Introduces MVMAE and MVMAE-V2T, reporting that they outperform supervised and vision-language baselines on three chest X-ray datasets; the prior covers a different X-ray research system."
prior_refs: ["memory:0dc7cef9-078c-80aa-a101-2212de66dbf8"]
source_url: "https://arxiv.org/abs/2511.22294"
source_urls: ["https://arxiv.org/abs/2511.22294"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:beats-supervised-biomedclip-and-chexagent-baselines-on-mimic-1a7014"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/beats-supervised-biomedclip-and-chexagent-baselines-on-mimic-1a7014/","markdown":"https://newruntime.com/posts/beats-supervised-biomedclip-and-chexagent-baselines-on-mimic-1a7014.md","json":"https://newruntime.com/posts/beats-supervised-biomedclip-and-chexagent-baselines-on-mimic-1a7014.json"}
---

# Beats supervised, BiomedCLIP, and CheXagent baselines on MIMIC-CXR, CheXpert, and PadChest.

## Retrieval answer

A revised paper, “Structure is Supervision: Multiview Masked Autoencoders for Radiology,” describes MVMAE, a self-supervised pretraining framework for radiology studies with multiple image views.

A revised paper, “Structure is Supervision: Multiview Masked Autoencoders for Radiology,” describes MVMAE, a self-supervised pretraining framework for radiology studies with multiple image views. It combines masked image reconstruction with cross-view alignment to learn view-invariant, disease-relevant representations.

The authors also introduce MVMAE-V2T, which uses radiology reports as an auxiliary training signal while retaining vision-only inference. They evaluate downstream disease classification on the public MIMIC-CXR, CheXpert, and PadChest datasets, reporting that MVMAE outperforms supervised and vision-language baselines. MVMAE-V2T reports further gains, particularly in lower-label settings.

The arXiv record lists the first submission on November 27, 2025 and version 5 on October 21, 2026, with a TMLR 2026 journal reference. The paper does not establish clinical safety, prospective performance, regulatory clearance, deployment in care settings, or public availability of a production model.

Source: https://arxiv.org/abs/2511.22294

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)