Title Here
Papers
- PReLU: Yet Another Single-Layer Solution to the XOR Problem
- GLU Variants Improve Transformer
- ClusterMap: compare multiple single cell RNA-Seq datasets across different experimental conditions
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Genie: Generative Interactive Environments
- Neuroscience-Inspired Artificial Intelligence
Links
- https://www.cell.com/neuron/fulltext/S0896-6273(24)00276-9 A latent pool of neurons silenced by sensory-evoked inhibition can be recruited to enhance perception
- https://pmc.ncbi.nlm.nih.gov/articles/PMC6874527/pdf/11538_2018_Article_415.pdf High-Dimensional Brain: A Tool for Encoding and Rapid Learning of Memories by Single Neurons
- https://www.cell.com/neuron/abstract/S0896-6273(24)00121-1 Simultaneous, cortex-wide dynamics of up to 1 million neurons reveal unbounded scaling of dimensionality with neuron number
- https://www.nature.com/articles/s41593-023-01514-1 Inferring neural activity before plasticity as a foundation for learning beyond backpropagation
- https://www.nature.com/articles/s41586-019-1346-5 High-dimensional geometry of population responses in visual cortex
- https://www.nature.com/articles/s41586-020-03044-3 Cortical response selectivity derives from strength in numbers of synapses
- https://www.nature.com/articles/s41586-020-2130-2 Fundamental bounds on the fidelity of sensory cortical coding
- https://www.nature.com/articles/s41467-024-48374-2 Primacy of vision shapes behavioral strategies and neural substrates of spatial navigation in marmoset hippocampus
- https://press.princeton.edu/ideas/the-dark-neuron-problem-or-mind-reading-at-90-accuracy The dark neuron problem, or mind reading at 90% accuracy
- https://vergenet.net/~conrad/boids/pseudocode.html Boids Pseudocode
- https://evolution.berkeley.edu/bottlenecks-and-founder-effects/ Bottlenecks and founder effects
- https://blog.eleuther.ai/rotary-embeddings/ Rotary Embeddings: A Relative Revolution
- https://people.math.ethz.ch/~salamon/PREPRINTS/diffgeo.pdf Introduction to Differential Geometry
- https://www.biorxiv.org/content/10.1101/2024.09.27.615483v2 The oneirogen hypothesis: modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms
- https://polyhedra.tessera.li/ Polyhedra Viewer
- https://playground.mujoco.org/ MuJoCo Playground
- https://pmc.ncbi.nlm.nih.gov/articles/PMC5019422/ The Computational Properties of a Simplified Cortical Column Model
- https://en.algorithmica.org Algorithmica
- https://medium.com/the-spike/2024-a-review-of-the-year-in-neuroscience-84d343155146 2024: A Review of the Year in Neuroscience
- https://medium.com/the-spike/your-cortex-contains-17-billion-computers-9034e42d34f2 Your Cortex Contains 17 Billion Computers
- https://biorxiv.org/content/10.1101/2024.12.29.630683v1 NeuroTorch: A Python library for neuroscience-oriented machine learning
- https://github.com/norse/norse Norse: A deep learning library for spiking neural networks
- https://snntorch.readthedocs.io/en/latest/index.html snnTorch
- https://latent.space/p/2025-papers The 2025 AI Engineer Reading List
- https://rwkv.com RWKV Language Model
- https://jcarlosroldan.com/post/348 What is SwiGLU?
- https://github.com/mesozoic-egg/tinygrad-notes/blob/main/20240102_jit.md JIT in tinygrad
- https://thoughtforms.life/meet-the-anthrobots-a-new-living-entity-with-much-to-teach-us/ Meet the Anthrobots: a new living entity with much to teach us
- https://en.m.wikipedia.org/wiki/Go_strategy_and_tactics Go strategy and tactics
- https://senseis.xmp.net Sensei's Library
- https://cacm.acm.org/research/deep-learning-for-ai/ Deep Learning for AI
- https://medium.com/swlh/physics-based-simulation-via-backpropagation-on-energy-functions-6d3b0e93f5fb Physics-based simulation via backpropagation on energy functions
- https://juniorrojas.com/algovivo/ algovivo: an energy-based formulation for soft-bodied virtual creatures
- https://practicapp.com/carbagepilot-part1/ Self-driving 1993 Volvo 940 (part 1: actuators)
- https://benjamincongdon.me/blog/2021/08/17/B-Trees-More-Than-I-Thought-Id-Want-to-Know/ B-Trees: More Than I Thought I'd Want to Know
- https://rowansci.com/tools/conformers Conformers
- https://oneusefulthing.org/p/scaling-the-state-of-play-in-ai Scaling The State of Play in AI
- https://daniel-bethell.co.uk/posts/kan/ Demystifying Kolmogorov-Arnold Networks: A Beginner-Friendly Guide with Code
- https://en.m.wikipedia.org/wiki/Helmholtz_machine Helmholtz machine
- https://sciencedirect.com/science/article/pii/S009286742031388X The Tolman-Eichenbaum Machine: Unifying Space and Relational Memory through Generalization in the Hippocampal Formation
- https://science.org/doi/10.1126/science.adk8261 Selection of experience for memory by hippocampal sharp wave ripples
- https://lifeiscomputation.com/breaking-free-from-neural-networks-and-dynamical-systems/ Breaking Free from Neural Networks and Dynamical Systems
- https://blog.val.town/blog/fast-follow/ What we learned copying all the best code assistants
- https://en.m.wikipedia.org/wiki/Attractor_network Attractor network
- https://nature.com/articles/s41583-022-00642-0 Attractor and integrator networks in the brain
- https://en.m.wikipedia.org/wiki/Gene_expression_programming Gene expression programming
- https://royalsocietypublishing.org/doi/10.1098/rsfs.2022.0029 On Bayesian mechanics: a physics of and by beliefs
- https://thetransmitter.org/this-paper-changed-my-life/this-paper-changed-my-life-a-massively-parallel-architecture-for-a-self-organizing-neural-pattern-recognition-machine-by-carpenter-and-grossberg This paper changed my life: ‘A massively parallel architecture for a self-organizing neural pattern recognition machine,’ by Carpenter and Grossberg
- https://js13kgames.com Js13kGames - The coding competition for web game developers, with a 13KB size limit
- https://bookramblings.blog/2024/07/09/love-triangle-matt-parker/ Book Ramblings: Love Triangle – Matt Parker
- https://arxiv.org/abs/2408.16737 Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
- https://operating-system-in-1000-lines.vercel.app/en Operating System in 1,000 Lines
- https://ollama.com OLlama - Get up and running with large language models.
- https://huyenchip.com//2025/01/07/agents.html Agents
- https://thetransmitter.org/neural-coding/most-neurons-in-mouse-cortex-defy-functional-categories/ Most neurons in mouse cortex defy functional categories
- https://huggingface.co/blog/matryoshka Introduction to Matryoshka Embedding Models
- https://internationalbrainlab.com International Brain Laboratory
- https://biorxiv.org/content/10.1101/2024.11.15.623878v2 Rarely categorical, always high-dimensional: how the neural code changes along the cortical hierarchy
- https://arxiv.org/abs/2310.06816 Text Embeddings Reveal (Almost) As Much As Text
- https://p.migdal.pl/blog/2025/01/dont-use-cosine-similarity Don't use cosine similarity carelessly
- https://openreview.net/forum?id=r1eBeyHFDH A Theory of Usable Information under Computational Constraints
- https://arxiv.org/abs/1805.04770 Born Again Neural Networks
- https://sakana.ai/transformer-squared/ Transformer²: Self-Adaptive LLMs
- https://contraptions.venkateshrao.com/p/the-gramsci-gap The Gramsci Gap
- https://space.ong.ac/escaping-flatland escaping flatland: career advice for CS undergrads
- https://josef.cn/blog/uk-talent UK's elite hardware talent is being wasted
- https://arxiv.org/abs/2501.09038 Do generative video models learn physical principles from watching videos?
- https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1517231/full The amygdala and the pursuit of future rewards
- https://oasis-model.github.io Oasis: A Universe in a Transformer
- https://lastexam.ai/ Humanity's Last Exam
- https://www.cell.com/trends/cognitive-sciences/fulltext/S1364-6613%2824%2900075-5 The Thermodynamics of Mind
- https://qwenlm.github.io/blog/qwen2.5-1m/ Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens
- https://www.thetransmitter.org/basal-ganglia/newly-characterized-striatal-circuits-add-twist-to-go-no-go-model-of-movement-control Newly characterized striatal circuits add twist to ‘go/no-go’ model of movement control
- https://umap-learn.readthedocs.io/en/latest/supervised.html UMAP for Supervised Dimension Reduction and Metric Learning
- https://pmc.ncbi.nlm.nih.gov/articles/PMC6028313/ The cognitive map in humans: Spatial navigation and beyond
- https://en.m.wikipedia.org/wiki/Long-term_potentiation Long-term potentiation
- https://www.nature.com/articles/s41586-018-0102-6 Vector-based navigation using grid-like representations in artificial agents
- https://en.m.wikipedia.org/wiki/Limit_cycle Limit cycle
- https://huggingface.co/blog/open-r1 Open-R1: a fully open reproduction of DeepSeek-R1
- https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1 The Illustrated DeepSeek-R1
- https://deepmind.google/discover/blog/genie-2-a-large-scale-foundation-world-model/ Genie 2: A large-scale foundation world model
- https://deepmind.google/discover/blog/navigating-with-grid-like-representations-in-artificial-agents/ Navigating with grid-like representations in artificial agents
- https://lodev.org/cgtutor/raycasting.html Lode's Computer Graphics Tutorial - Raycasting
- https://weblog.jamisbuck.org/2011/2/7/maze-generation-algorithm-recap Maze Generation: Algorithm Recap
- https://ipsitransactions.org/journals/papers/tir/2019jan/p5.pdf Analysis of Maze Generating Algorithms
- http://www.cse.yorku.ca/%7Eamana/research/grid.pdf A Fast Voxel Traversal Algorithm for Ray Tracing
- https://arxiv.org/abs/2402.03300 DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- https://epoch.ai/gradient-updates/how-has-deepseek-improved-the-transformer-architecture How has DeepSeek improved the Transformer architecture?
- https://aman.ai/primers/ai/deepseek-R1 Primers - DeepSeek-R1
- https://arxiv.org/abs/2202.04200 MaskGIT: Masked Generative Image Transformer
- https://arxiv.org/abs/2501.14926 Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
- https://arxiv.org/abs/2501.16496 Open Problems in Mechanistic Interpretability
- https://arcprize.org/blog/r1-zero-r1-results-analysis An Analysis of DeepSeek's R1-Zero and R1
- http://beza1e1.tuxen.de/lore/story_of_mel.html The Story of Mel
- https://arxiv.org/abs/2408.05446 Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
- https://nature.com/articles/s42003-024-07282-3 Recurrent neural networks with transient trajectory explain working memory encoding mechanisms