IAMJB
@iamjbd.bsky.social
🤗 ML at Hugging Face
🌲 Academic Staff at Stanford University (AIMI Center)
🦴 Radiology AI is my stuff
🌲 Academic Staff at Stanford University (AIMI Center)
🦴 Radiology AI is my stuff
💥 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.
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.
June 12, 2025 at 2:17 PM
💥 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.
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.
💥 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
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
June 9, 2025 at 3:13 PM
💥 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
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
www.nature.com/articles/s4...
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...
www.nature.com
April 16, 2025 at 4:18 PM
Sociodemographic biases in medical decision making by large language models
www.nature.com/articles/s4...
www.nature.com/articles/s4...
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)
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.
huggingface.co
March 14, 2025 at 8:55 PM
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)
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!
@radiology_rsna, colleagues at stanford dive into how foundation models (FMs) are set to revolutionize radiology!
March 10, 2025 at 10:44 PM
🧵 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!
@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...
What a trick...
February 3, 2025 at 5:54 PM
"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...
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.
🤯 3,000 expert-level questions across 100+ subjects, created by nearly 1,000 subject matter experts globally.
January 25, 2025 at 7:00 PM
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.
🤯 3,000 expert-level questions across 100+ subjects, created by nearly 1,000 subject matter experts globally.
DeepSeek-R1: next level
January 25, 2025 at 5:14 AM
DeepSeek-R1: next level
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).
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).
January 24, 2025 at 5:50 PM
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).
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.
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.
January 19, 2025 at 6:09 PM
🧩 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.
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.
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.
January 16, 2025 at 6:00 PM
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...
>> Hybrid linear-softmax attention working very well at large scale and long-context
filecdn.minimax.chat/_Arxiv_MiniM...
January 15, 2025 at 10:33 PM
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...
>> 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
arxiv.org/pdf/2501.07301
January 15, 2025 at 4:38 AM
first look into what the Qwen team used to develop QwQ
arxiv.org/pdf/2501.07301
arxiv.org/pdf/2501.07301
Neat: Representing Long Volumetric Video with Temporal Gaussian Hierarchy
Contrib: Temporal Gaussian Hierarchy representation for long volumetric video.
Contrib: Temporal Gaussian Hierarchy representation for long volumetric video.
January 14, 2025 at 2:32 AM
Neat: Representing Long Volumetric Video with Temporal Gaussian Hierarchy
Contrib: Temporal Gaussian Hierarchy representation for long volumetric video.
Contrib: Temporal Gaussian Hierarchy representation for long volumetric video.
Nice visualization of RAG vs. Agentic RAG
January 13, 2025 at 5:37 PM
Nice visualization of RAG vs. Agentic RAG
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
January 12, 2025 at 4:33 AM
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
volume rendering made easy and free 😍
January 10, 2025 at 7:23 PM
volume rendering made easy and free 😍
How do you even coordinate this?
January 8, 2025 at 9:04 PM
How do you even coordinate this?
🚀 PRIME + Eurus-2 beat Qwen2.5-Math-Instruct with 1/10 the data!
✨ Implicit PRM (no labels)
🔄 Online updates, zero overhead
🎯 Token-level rewards + RLOO
Scaling up with 3x more data!
✨ Implicit PRM (no labels)
🔄 Online updates, zero overhead
🎯 Token-level rewards + RLOO
Scaling up with 3x more data!
January 5, 2025 at 9:06 PM
🚀 PRIME + Eurus-2 beat Qwen2.5-Math-Instruct with 1/10 the data!
✨ Implicit PRM (no labels)
🔄 Online updates, zero overhead
🎯 Token-level rewards + RLOO
Scaling up with 3x more data!
✨ Implicit PRM (no labels)
🔄 Online updates, zero overhead
🎯 Token-level rewards + RLOO
Scaling up with 3x more data!
Super interesting read:
www.thelancet.com/journals/la...
www.thelancet.com/journals/la...
January 4, 2025 at 1:00 PM
Super interesting read:
www.thelancet.com/journals/la...
www.thelancet.com/journals/la...
2 OLMo 2 Furious captures every lesson learned since OLMo 1, featuring in-depth explorations of:
• Stable pretraining
• LR annealing, data curricula, and soups
• Tulu post-training
• Compute infrastructure
• Stable pretraining
• LR annealing, data curricula, and soups
• Tulu post-training
• Compute infrastructure
January 4, 2025 at 3:14 AM
2 OLMo 2 Furious captures every lesson learned since OLMo 1, featuring in-depth explorations of:
• Stable pretraining
• LR annealing, data curricula, and soups
• Tulu post-training
• Compute infrastructure
• Stable pretraining
• LR annealing, data curricula, and soups
• Tulu post-training
• Compute infrastructure
Top 25 Open Source AI models on Hugging Face in 2025
December 31, 2024 at 12:47 AM
Top 25 Open Source AI models on Hugging Face in 2025
💥 Gemini 2.0 is on paper-central. Talk with any paper from the 🤗 Hugging Face paper page. Example with GenEx 👇
December 16, 2024 at 6:40 PM
💥 Gemini 2.0 is on paper-central. Talk with any paper from the 🤗 Hugging Face paper page. Example with GenEx 👇
EasyRef is on 🤗 Hugging Face
After DiffSensei yesterday, @ylecun is once again being style-transferred!
(⚡Llama 3.3) Chat with the paper: huggingface.co/spaces/hugg...
🤗 Model: huggingface.co/zongzhuofan...
🤗 Demo: huggingface.co/spaces/zong...
🤗 Paper: huggingface.co/papers/2412...
After DiffSensei yesterday, @ylecun is once again being style-transferred!
(⚡Llama 3.3) Chat with the paper: huggingface.co/spaces/hugg...
🤗 Model: huggingface.co/zongzhuofan...
🤗 Demo: huggingface.co/spaces/zong...
🤗 Paper: huggingface.co/papers/2412...
December 13, 2024 at 6:04 PM
EasyRef is on 🤗 Hugging Face
After DiffSensei yesterday, @ylecun is once again being style-transferred!
(⚡Llama 3.3) Chat with the paper: huggingface.co/spaces/hugg...
🤗 Model: huggingface.co/zongzhuofan...
🤗 Demo: huggingface.co/spaces/zong...
🤗 Paper: huggingface.co/papers/2412...
After DiffSensei yesterday, @ylecun is once again being style-transferred!
(⚡Llama 3.3) Chat with the paper: huggingface.co/spaces/hugg...
🤗 Model: huggingface.co/zongzhuofan...
🤗 Demo: huggingface.co/spaces/zong...
🤗 Paper: huggingface.co/papers/2412...