Feburary
Papers
Links
- https://www.jneurosci.org/content/35/36/12412 Temporal Processing Capacity in High-Level Visual Cortex Is Domain Specific
- https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2020.617187/full Windows of Integration Hypothesis Revisited
- https://www.nature.com/articles/343644a0 A dimension reduction framework for understanding cortical maps
- https://www.biorxiv.org/content/10.1101/2024.08.06.606687v2.full Local lateral connectivity is sufficient for replicating cortex-like topographical organization in deep neural networks
- https://pubmed.ncbi.nlm.nih.gov/32223436/ Effective Dimensionality: A Tutorial
- https://www.brain-score.org/ Brain-Score
- https://www.nature.com/articles/s41467-025-56297-9 Dendrites endow artificial neural networks with accurate, robust and parameterefficient learning
- https://magic-with-latents.github.io/latent/posts/ddpms/part2/ All you need to know about Gaussian distribution
- https://medium.com/@sahin.samia/the-math-behind-deepseek-a-deep-dive-into-group-relative-policy-optimization-grpo-8a75007491ba The Math Behind DeepSeek: A Deep Dive into Group Relative Policy Optimization (GRPO)
- https://www.lesswrong.com/posts/dLbkrPu5STNCBLRjr/applause-lights Applause Lights
- https://www.math.uri.edu/~thoma/comp_top__2018/stag2016.pdf Persistent homology: a step-by-step introduction for newcomers
- https://graphsandnetworks.com/what-is-persistent-homology/ What is persistent homology?
- https://www.biorxiv.org/content/10.1101/2024.12.06.627299v1 SubCell: Vision foundation models for microscopy capture single-cell biology
- https://www.biorxiv.org/content/10.1101/2024.10.23.619972v1.full scGenePT: Is language all you need for modeling single-cell perturbations?
- https://docs.modula.systems/examples/weight-erasure/ Weight erasure
- https://superb-makemake-3a4.notion.site/group-relative-policy-optimization-GRPO-18c41736f0fd806eb39dc35031758885 Group relative policy optimization (GRPO)
- https://rlhfbook.com A Little Bit of Reinforcement Learning from Human Feedback
- https://arxiv.org/abs/2412.02975 Theoretical limitations of multi-layer Transformer
- https://arxiv.org/abs/2412.05265 Reinforcement Learning: An Overview
- https://deepmind.google/discover/blog/open-sourcing-deepmind-lab/ Open-sourcing DeepMind Lab
- https://nature.com/articles/s41593-024-01868-0 The architecture of the human default mode network explored through cytoarchitecture, wiring and signal flow
- https://nature.com/articles/s41586-024-08527-1 Left–right-alternating theta sweeps in entorhinal–hippocampal maps of space
- https://jax-ml.github.io/scaling-book/ How to Scale Your Model
- https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-reasoning-llms A Visual Guide to Reasoning LLMs
- https://arxiv.org/abs/2502.00873 Language Models Use Trigonometry to Do Addition
- https://iclr-blog-track.github.io/2022/03/25/ppo-implementation-details/ The 37 Implementation Details of Proximal Policy Optimization
- https://nickmcd.me Nick's Blog
- https://geohot.github.io/blog/jekyll/update/2025/01/22/death-of-the-visceral.html Death of the Visceral
- https://substack.com/@maartengrootendorst/p-141228095 A Visual Guide to Mamba and State Space Models
- https://substack.com/@maartengrootendorst/p-148217245 A Visual Guide to Mixture of Experts (MoE)
- https://thetransmitter.org/animal-models/neural-barcodes-help-seed-stashing-birds-recall-their-hidden-hauls/ Neural ‘barcodes’ help seed-stashing birds recall their hidden hauls
- https://nature.com/articles/nature13665 Neural constraints on learning
- https://thetransmitter.org/neural-dynamics/neural-manifolds-latest-buzzword-or-pathway-to-understand-the-brain/ Neural manifolds: Latest buzzword or pathway to understand the brain?
- https://arxiv.org/abs/2502.05171 Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- https://brandonrohrer.com/transformers Transformers from Scratch
- https://ldeming.com/longevityfaq Longevity FAQ: A beginner's guide to longevity research
- https://paulbutler.org/2025/smuggling-arbitrary-data-through-an-emoji/ Smuggling arbitrary data through an emoji
- https://press.asimov.com/articles/gene-circuit The Making of a Gene Circuit
- https://cell.com/device/fulltext/S2666-9986(24)00603-3?rss=yes SpiRobs: Logarithmic spiral-shaped robots for versatile grasping across scales
- https://arxiv.org/abs/2407.18384 Mathematical theory of deep learning
- https://caiac.pubpub.org/pub/m4ue9ykj/release/1 General Deep Reinforcement Learning in NES Games
- https://macmillanlearning.com/college/us/preview/icb Interactive Cell Biology
- https://novasky-ai.github.io/posts/sky-t1/ Sky-T1: Train your own O1 preview model within $450
- https://pyspur.dev/blog/introduction_cuda_programming Introduction to CUDA Programming for Python Developers
- https://arxiv.org/abs/2502.05475 You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
- https://paulgraham.com/richnow.html How People Get Rich Now
- https://medium.com/@joaolages/kv-caching-explained-276520203249 Transformers KV Caching Explained
- https://kazemnejad.com/blog/transformer_architecture_positional_encoding/ Transformer Architecture: The Positional Encoding
- https://huggingface.co/blog/designing-positional-encoding You could have designed state of the art positional encoding
- https://huggingface.co/blog/billion-classifications 1 Billion Classifications
- https://github.com/rom1504/img2dataset img2dataset
- https://huggingface.co/blog/static-embeddings Train 400x faster Static Embedding Models with Sentence Transformers
- https://nature.com/articles/s41593-024-01845-7 Dynamical constraints on neural population activity
- https://0ver.org ZeroVer: 0-based Versioning
- https://mesozoic-egg.github.io/tinygrad-notes/ Tutorials on Tinygrad
- https://152334h.github.io/blog/non-determinism-in-gpt-4/ Non-determinism in GPT-4 is caused by Sparse MoE
- https://jiha-kim.github.io/posts/introduction-to-stochastic-calculus/ Introduction to Stochastic Calculus
- https://ericdaigle.ca/posts/breaking-into-dozens-of-apartments-in-five-minutes/ Breaking into dozens of apartment buildings in five minutes on my phone
- https://latent-planning.github.io Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
- https://noperator.dev/posts/document-ranking-for-complex-problems/ Hard problems that reduce to document ranking
- https://localghost.dev/blog/this-page-is-under-construction/ This page is under construction
- https://docs.vlm.run/introduction What is VLM Run?
- https://en.m.wikipedia.org/wiki/Convolution_theorem Convolution theorem
- https://en.m.wikipedia.org/wiki/Arborescence_(graph_theory) Arborescence (graph theory)
- https://en.m.wikipedia.org/wiki/B%2B_tree B+ tree
- https://www.inceptionlabs.ai/news Introducing Mercury, the first commercial-scale diffusion large language model
- https://arxiv.org/abs/2310.16834 Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
- https://arxiv.org/abs/2406.07524 Simple and Effective Masked Diffusion Language Models
- https://coffeebeforearch.github.io/2020/06/23/mmul.html Optimizing Matrix Multiplication
- https://siboehm.com/articles/22/CUDA-MMM How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklog
- https://www.runpulse.com/blog/why-llms-suck-at-ocr Why LLMs Suck at OCR
- https://nroottag.github.io/ Tracking You from a Thousand Miles Away! Turning a Bluetooth Device into an Apple AirTag Without Root Privileges
- https://arxiv.org/pdf/2407.06581v1 Vision language models are blind
- https://pmc.ncbi.nlm.nih.gov/articles/PMC10925082/ Ribonanza: deep learning of RNA structure through dual crowdsourcing
- https://en.wikipedia.org/wiki/Template_modeling_score Template modeling score
- https://www.pnas.org/doi/10.1073/pnas.2112677119 Thoughts on how to think (and talk) about RNA structure
- https://en.wikipedia.org/wiki/Pseudoknot Pseudoknot
- https://eternagame.org/challenges/11843006 OpenKnot
- https://www.nature.com/articles/s41592-022-01605-0 RNA secondary structure packages evaluated and improved by high-throughput experiments