New preprint! In a few words: we don't think you should use leave-one-out cross-validation (LOOCV). In a lot of words (+RebalancedCV, a LOOCV alternative): arxiv.org/abs/2406.01652 In a thread:

Paradigm challenged: gene expression is driven by DNA sequence variants with little contribution by methylation nature.com/articles/s4158… Nature Genetics deCODE genetics Oxford Nanopore nature.com/articles/s4158…

The therapeutic landscape of #ITP treatments is expanding rapidly. If you want to be updated about what is coming, this is a great article discussing the clinical trials of the main products in development. tinyurl.com/4377d9k9

Introducing The AI Scientist: The world’s first AI system for automating scientific research and open-ended discovery! sakana.ai/ai-scientist/ From ideation, writing code, running experiments and summarizing results, to writing entire papers and conducting peer-review, The AI

T. Greer I think it's stratified by generation, but here's an attempt. (This isn't the list of books that I think one ought to read -- it's just the list that I think roughly covers the major ideas that are influential here.) The Tinkerings of Robert Noyce Seeing Like a State The Dream

Excited to share our new paper KAN 2.0: Kolmogorov-Arnold Networks meet Science 🚀 The problem with AI + Science is that these two disciplines use different "languages" (connectionism vs symbolism). KAN 2.0 attempts to unify them: smooth transitions from science to KAN and back.

KAN fused with XGBoost is 🔥 🔥 🔥 “KAN-XGBoost algorithm outperforms both MLP and KAN algorithms across all the evaluated metrics. Notably, KAN-XGBoost produces an accuracy of 99.69%, a precision of 98.1%, a recall of 98.01%, and an F1-score of 98.04%. While KAN alone

This week in Nature: Space Omics – Biomedical atlas captures health effects of spaceflight. Browse the full issue: nature.com/nature/volumes…

If you’d like to spend a few hours this weekend to dive into Large Language Models (LLMs) and understand how they work, I've prepared a 3-hour coding workshop presentation on implementing, training, and using LLMs: youtube.com/watch?v=quh7z1…

Benchmarking >80 LLMs shows: The best model is not necessarily the best for your programming language 😱 - Best overall: Anthropic’s Sonnet 3.5 - Best for Go: Meta’s Llama 3.1 405B - Best for Java: OpenAI’s GPT-4 Turbo - Best for Ruby: OpenAI’s GPT-4o Good models for one

If you embed an entire document, you'll lose retrieval precision. If you chunk a document, you'll lose contextual information between chunks. These are some concerns when you're building long-context RAG applications. But "Late chunking" may just be the sweet spot in the

I really like this schematic from Koichi Takahashi at #iWAL24 on phenotypic shifts in AML after ven-based therapies … don’t underestimate the tiny monocytic & erythroid clones.. they will come back & haunt you!! Food for thought for us #hematopathologist we need to report and track

Fundamental equations linking methylation dynamics to maximum lifespan in mammals nature.com/articles/s4146…

🧵Thread on frontline caplacizumab and plasma exchange in TTP🚨 With advancing care for immune thrombotic thrombocytopenic purpura (iTTP), let’s discuss frontline caplacizumab (capla) and the future for therapeutic plasma exchange (TPE) ⤵️ #hemetwitter #TTP #caplacizumab 1/22

Finally out in Nature Protocols : our group's workflows for end to end computational pathology. Compatible with UNI and other foundation models. Led by Omar S.M. El Nahhas from katherlab journal link: nature.com/articles/s4159… full text: rdcu.be/dT35l

Kolmogorov-Arnold Transformer discuss: huggingface.co/papers/2409.10… Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the

Moshi is a very nice/fun conversational AI audio 🔊 model release from kyutai . Are you slowly losing faith in the objective reality and existence of Advanced Voice Mode? Talk to Moshi instead :) You can talk to it on their website: moshi.chat Or even locally

No author has shaped my worldview more than Nassim Taleb (Nassim Nicholas Taleb). I stumbled on The Black Swan eight years ago, then inhaled the rest of the Incerto. I've increasingly come to appreciate the importance of its ideas to prolonging the human story. Was an honour to speak with

Review on #AML therapy MD Anderson Cancer Center #Leukemia Blood Cancer Journal doi.org/10.1038/s41408… #leusm