Lightnews — Scholar-powered news

IAMJB

@iamjbd.bsky.social

1.8K followers 1.2K following 94 posts

🤗 ML at Hugging Face 🌲 Academic Staff at Stanford University (AIMI Center) 🦴 Radiology AI is my stuff

Posts Media Videos Starter Packs

IAMJB @iamjbd.bsky.social · Jun 12

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

IAMJB @iamjbd.bsky.social · Jun 12

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

IAMJB @iamjbd.bsky.social · Jun 12

📄 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! 🤝

Structuring with Lightweight Models - a StanfordAIMI Collection

IAMJB @iamjbd.bsky.social · Jun 12

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.

IAMJB @iamjbd.bsky.social · Jun 12

💥 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.

IAMJB @iamjbd.bsky.social · Jun 9

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...

Structured Radiology Reports - a StanfordAIMI Collection

IAMJB @iamjbd.bsky.social · Jun 9

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.

IAMJB @iamjbd.bsky.social · Jun 9

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.

IAMJB @iamjbd.bsky.social · Jun 9

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.

IAMJB @iamjbd.bsky.social · Jun 9

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.

IAMJB @iamjbd.bsky.social · Jun 9

💥 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

IAMJB @iamjbd.bsky.social · Apr 16

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

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...

IAMJB @iamjbd.bsky.social · Mar 14

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)

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.

IAMJB @iamjbd.bsky.social · Mar 10

🧵 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!

IAMJB @iamjbd.bsky.social · Feb 3

"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...

IAMJB @iamjbd.bsky.social · Jan 25

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.

IAMJB @iamjbd.bsky.social · Jan 25

DeepSeek-R1: next level

IAMJB @iamjbd.bsky.social · Jan 24

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?👇

IAMJB @iamjbd.bsky.social · Jan 24

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.

IAMJB @iamjbd.bsky.social · Jan 24

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).

IAMJB @iamjbd.bsky.social · Jan 19

🧩 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.

IAMJB @iamjbd.bsky.social · Jan 17

IAMJB @iamjbd.bsky.social · Jan 16

Oops. Thanks!

IAMJB @iamjbd.bsky.social · Jan 16

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.

IAMJB @iamjbd.bsky.social · Jan 15

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...