This work builds on our recent study on Automated Structured Radiology Report Generation (x.com/IAMJBDEL/st...) which introduces the dataset and evaluation framework.

Huge thanks to the amazing team at Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI): Johannes Moll, Louisa Fay, @asfandyar_azhar, @SophieOstmeier, Tim Lueth, Sergios Gatidis, @curtlanglotz

Structuring with Lightweight Models - a StanfordAIMI Collection

📄 Paper: arxiv.org/abs/2506.00200
🌐 Project Page: stanford-aimi.github.io/structuring...
🤗 Models & Data: huggingface.co/collections...
All models and datasets are fully open-source — we hope this contributes to the broader medical AI community! 🤝

We benchmark lightweight models (<300M params) against state-of-the-art LLMs (up to 70B params), using human-reviewed test data and clinically grounded evaluation metrics. Our results highlight the strong potential of specialized, efficient models in clinical NLP application.

💥 Excited to share our latest work: Structuring Radiology Reports: Challenging LLMs with Lightweight Models

In this study, we explore how small, task-specific encoder-decoder models can rival (and sometimes outperform) much larger LLMs; all while being faster, cheaper, and easier to deploy.

ons.

Structured Radiology Reports - a StanfordAIMI Collection

Paper, soon to appear at #ACL2025 main: arxiv.org/pdf/2505.24223
Project page, with all resources (datasets, models, ontology) and usage notes: stanford-aimi.github.io/srrg.html
All models and datasets are publicly available as open-source:
huggingface.co/collections...

4) We conduct a reader study to create a radiologist-validated test set for both the automated structured radiology report task, as well as utterances disease labels from our new ontology.

Finally, external evaluation is conducted using out-of-institution data by @hopprai.

3) We fine-tune popular RRG system on this restructured findings and impression, namely:
- Chexagent @StanfordAIMI
- MAIRA-2 @MSFTResearch
- RaDialog @TU_Muenchen
- Chexpert-plus @StanfordAIMI

As well as a BERT architecture for the disease classification system on our new ontology.

2) Since each reported observation, whether in the findings or impression sections, is expressed as a single utterance (1.5M unique utterances in total), we use a large language model to label each one according to a new ontology comprising 72 critical chest X-ray (CXR) observations.

1) We leverage LLM to restructure MIMIC-CXR and Chexpert-plus (180K Findings sections and 400K Impression sections) into reports categorized by organ system, under strict rules.

💥 We unveil our paper accepted at the #ACL2025 Main Conference:
Automated Structured Report Generation

Let's revisit automated radiology report generation for CXR.
Free-form reports make it hard for AI systems to learn accurate generation, and even harder to evaluate. 🧵👇
@StanfordAIMI @hopprai

Sociodemographic biases in medical decision making by large language models Nature Medicine - A panel of nine LLMs was exposed to simulated clinical cases with switched sociodemographic features exploring ethnic, social, sexual orientation and gender dimensions and showed...

Sociodemographic biases in medical decision making by large language models
www.nature.com/articles/s4...

IAMJB/chexpert-mimic-cxr-impression-baseline · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Just noticed our lightweight RRG model has been downloaded over 92,000 times this months on 🤗HuggingFace. This model was included in the CheXpert-Plus release and contains just 67 million parameters:
huggingface.co/IAMJB/chexpe...
Its also a top ranking model on RexRank (rexrank.ai)

🧵 What if AI could learn from millions of unlabeled radiology images and reports—and then flexibly adapt to new clinical tasks? In a new comprehensive review in
@radiology_rsna, colleagues at stanford dive into how foundation models (FMs) are set to revolutionize radiology!

"Second, we develop budget forcing to control test-time compute by forcefully terminating the model's thinking process or lengthening it by appending "Wait" multiple times to the model's generation when it tries to end."

What a trick...

Is this the last benchmark before AGI? Humanity's Last Exam (HLE)

🤯 3,000 expert-level questions across 100+ subjects, created by nearly 1,000 subject matter experts globally.

DeepSeek-R1: next level

𝟱. Working Memory: Compiles long-term and task memory to create the final prompt for the LLM.

Typically, 1–3 = Long-Term Memory; 5 = Short-Term Memory.

Thoughts on agent memory?👇

𝟮. Semantic Memory: External/grounding knowledge or self-knowledge, similar to RAG context.
𝟯. Procedural Memory: System setup details like prompts, tools, and guardrails (stored in Git/registries).
𝟰. Task Memory: Info retrieved from long-term storage for immediate tasks.

𝗔 𝗦𝗶𝗺𝗽𝗹𝗲 𝗚𝘂𝗶𝗱𝗲 𝘁𝗼 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗠𝗲𝗺𝗼𝗿𝘆 🌟

An agent's memory helps it plan and react by leveraging past interactions or external data via prompt context. Here’s a breakdown:

𝟭. Episodic Memory: Logs past actions/interactions (e.g., stored in a vector database for semantic search).

🧩 The future of creativity is elemental. ✨

Kling AI just announced Elements

🌎 First, world building:
Craft your characters, environments, props. Plan your motion and VFX.
🎛️ Then, remixing:
Bring it all together into a cohesive story.

Oops. Thanks!

Amazing. Agent Roles:
⛳ PhD Agent: Conducts literature reviews, interprets results, writes reports.
⛳ Postdoc Agent: Plans research, designs experiments.
⛳ ML Engineer Agent: Prepares data, writes, optimizes code.
⛳ Professor Agent: Oversees, refines reports.

MiniMax-01 is Now Open-Source: Scaling Lightning Attention for the AI Agent Era
>> Hybrid linear-softmax attention working very well at large scale and long-context
filecdn.minimax.chat/_Arxiv_MiniM...

first look into what the Qwen team used to develop QwQ
arxiv.org/pdf/2501.07301

Neat: Representing Long Volumetric Video with Temporal Gaussian Hierarchy

Contrib: Temporal Gaussian Hierarchy representation for long volumetric video.

Nice visualization of RAG vs. Agentic RAG

GitHub - CatchTheTornado/text-extract-api: Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Conver... Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured ...

github.com/CatchTheTorn...

Neat. Converts images, PDFs, and Office documents to Markdown or JSON using OCR and LLM models, with features for caching, distributed processing, and PII removal