March
Papers
- A Deep Dive into Single-Cell RNA Sequencing Foundation Models
- Gene2vec: distributed representation of genes based on co-expression
- scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings
- Bulk tissue cell type deconvolution with multi-subject single-cell expression reference
Links
- https://benhoyt.com/writings/go-1brc/ The One Billion Row Challenge in Go: from 1m45s to 3.4s in nine solutions
- https://newsletter.yongzx.io/p/ai-research-internship-search-as AI Research Internship Search as a CS PhD Student
- https://medium.com/@toporov.artem.ig/what-hands-say-2nd-place-in-the-kaggle-competition-code-of-the-winning-solution-3239caa78554 What Hands Say: 2nd Place in the Kaggle Competition + code of the winning solution
- https://www.alignmentforum.org/posts/xmegeW5mqiBsvoaim/we-inspected-every-head-in-gpt-2-small-using-saes-so-you-don We Inspected Every Head In GPT-2 Small using SAEs So You Don’t Have To
- https://www.neelnanda.io/blog/mini-blog-post-5-how-to-learn-from-conversations Mini Blog Post 5: How to Learn From Conversations
- https://www.neelnanda.io/blog/prioritisation Mini Blog Post 16: Prioritisation Part 1/2 - Finding Goals
- https://www.neelnanda.io/blog/32-macro-procrastination Post 32: Macro-Procrastination
- https://www.lesswrong.com/posts/P5k3PGzebd5yYrYqd/the-hamming-question The Hamming Question
- https://thegradient.pub/interpretability-in-ml-a-broad-overview/ Interpretability in Machine Learning: An Overview
- https://stacher.io/ Modern GUI for YT-DLP
- https://www.yitay.net/blog/training-great-llms-entirely-from-ground-zero-in-the-wilderness Training great LLMs entirely from ground up in the wilderness as a startup
- https://www.eleuther.ai/interpretability EleutherAI Interpretability Research
- https://transformer-circuits.pub/2024/qualitative-essay/index.html Reflections on Qualitative Research
- https://deepmind.google/discover/blog/specification-gaming-the-flip-side-of-ai-ingenuity/ Specification gaming: the flip side of AI ingenuity
- https://transformer-circuits.pub/2024/qualitative-essay/index.html Reflections on Qualitative Research
- https://en.wikipedia.org/wiki/Anscombe%27s_quartet Anscombe's quartet
- https://d3js.org/ A JavaScript library for bespoke data visualization
- https://web.stanford.edu/~jurafsky/slp3/ Speech and Language Processing (3rd ed. draft)
- https://developers.google.com/machine-learning/crash-course/classification/precision-and-recall Classification: Precision and Recall
- https://www.v7labs.com/blog/f1-score-guide F1 Score in Machine Learning: Intro & Calculation
- https://bostondynamics.com/blog/picking-up-momentum/ Picking Up Momentum - Boston Dynamics
- https://caduceus-dna.github.io/ Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling
- https://unsloth.ai/blog/gemma-bugs Fixing All Gemma Bugs
- https://github.com/openai/transformer-debugger Transformer Debugger - OpenAI
- https://brianfitzgerald.xyz/prompt-augmentation/ SuperPrompt - Better SDXL prompts in 77M Parameters
- https://pytorch.org/blog/what-every-user-should-know-about-mixed-precision-training-in-pytorch/ What Every User Should Know About Mixed Precision Training in PyTorch
- https://crookedtimber.org/2024/03/16/occasional-paper-when-armor-met-lips/ Occasional paper: When Armor Met Lips
- https://x.ai/blog/grok-os Open Release of Grok-1
- https://www.paulgraham.com/google.html How to Start Google
- https://jsomers.net/e-coli-chemotaxis/ The Baffling Intelligence of a Single Cell - The story of E. coli chemotaxis
- https://transformer-circuits.pub/2022/in-context-learning-and-induction-heads/index.html In-context Learning and Induction Heads
- https://mhamilton.net/featup.html FeatUp: A Model-Agnostic Framework for Features at Any Resolution
- https://sakana.ai/evolutionary-model-merge/ Evolving New Foundation Models: Unleashing the Power of Automating Model Development
- https://factorialfunds.com/blog/under-the-hood-how-openai-s-sora-model-works Under The Hood: How OpenAI's Sora Model Works
- https://developers.google.com/machine-learning/glossary Machine Learning Glossary
- https://corticallabs.com/research.html Cortical Labs Research
- https://www.science.org/doi/10.1126/science.aax6239 Dendritic action potentials and computation in human layer 2/3 cortical neurons
- https://siboehm.com/articles/22/CUDA-MMM How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklog
- https://www.biomage.net/blog/public-scrna-seq-data Leveraging Public scRNA-seq Data: A Guide to Repositories and Resources
- https://atcold.github.io/NYU-DLSP21/en/week15/15-1/ Joint Embedding Methods - Contrastive
- https://www.lesswrong.com/posts/rZPiuFxESMxCDHe4B/sae-reconstruction-errors-are-empirically-pathological SAE reconstruction errors are (empirically) pathological
- https://mobiusml.github.io/1bit_blog/ Towards 1-bit Machine Learning Models
- https://serre-lab.github.io/Lens/ LENS Project
- https://ai.meta.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/ Self-supervised learning: The dark matter of intelligence
- https://blog.oimo.io/2023/04/10/life-universe-en/ Life Universe: A Technical Explanation
- https://adamkarvonen.github.io/machine_learning/2024/03/20/chess-gpt-interventions.html Manipulating Chess-GPT's World Model
- https://r00tkitsmm.github.io/ R00tkitSMM Research Blog Posts
- https://www.lesswrong.com/posts/nAhy6ZquNY7AD3RkD/sae-vis-announcement-post-1 SAE-VIS: Announcement Post
- https://bigaidream.gitbooks.io/tech-blog/content/2014/de-mystifying-good-research.html?ref=ruder.io De-Mystifying Good Research and Good Papers (repost)