--- id: "/foundations/page/22/" title: "Foundations · page 22" creator: null creator_url: null creator_x: null url: "https://skillissue.dev/foundations/page/22/" level: null level_max: null category: null subcategory: null region: null license: null license_scope: null access: null models: null source_date: null date_added: null resource_kind: null verification_basis: null access_evidence: null domain_top: null domain_sub: null last_verified: null --- # Foundations Understand language models and choose a learning path. - [Llm Fundamentals](/foundations/llm-fundamentals/index.md) (139) - [Courses And Learning Paths](/foundations/courses-and-learning-paths/index.md) (179) - [From Scratch Implementations](/foundations/from-scratch-implementations/index.md) (1) - [Practitioner Overviews](/foundations/practitioner-overviews/index.md) (387) [Beginner](/foundations/beginner/index.md) [Intermediate](/foundations/intermediate/index.md) [Advanced](/foundations/advanced/index.md) [Expert](/foundations/expert/index.md) 706 resources · page 22 of 23 - ### [Relational inductive biases, deep learning, and graph networks](/foundations/llm-fundamentals/relational-inductive-biases-graph-networks/index.md) Creator not supplied; see original source. arXiv paper (2018) "Relational inductive biases, deep learning, and graph networks", defining the graph network block that unifies many GNN variants. Advanced–Expert · unknown · unknown resource · en - ### [ResNet](/foundations/llm-fundamentals/resnet/index.md) Creator not supplied; see original source. arXiv paper (2015) "Deep Residual Learning for Image Recognition", introducing ResNet residual networks. Advanced–Expert · unknown · unknown resource · en - ### [RL4CO](/foundations/llm-fundamentals/rl4co/index.md) Creator not supplied; see original source. RL4CO documentation: reinforcement-learning benchmark and library for combinatorial optimisation problems. Advanced · unknown · unknown resource · en - ### [RWKV](/foundations/llm-fundamentals/rwkv/index.md) Creator not supplied; see original source. arXiv paper (2023) introducing RWKV, a recurrent architecture trained in parallel like a transformer. Advanced–Expert · unknown · unknown resource · en - ### [Efficiently Modeling Long Sequences with Structured State Spaces (S4)](/foundations/llm-fundamentals/s4-structured-state-spaces/index.md) Creator not supplied; see original source. arXiv paper (2021) "Efficiently Modeling Long Sequences with Structured State Spaces", introducing S4, structured state space models for long sequences. Advanced–Expert · unknown · unknown resource · en - ### [SAC](/foundations/llm-fundamentals/sac/index.md) Creator not supplied; see original source. arXiv paper (2018) introducing Soft Actor-Critic (SAC), off-policy maximum-entropy deep reinforcement learning. Advanced–Expert · unknown · unknown resource · en - ### [SAM](/foundations/llm-fundamentals/sam/index.md) Creator not supplied; see original source. arXiv paper (2023) introducing Segment Anything (SAM), a promptable image segmentation model and dataset. Advanced–Expert · unknown · unknown resource · en - ### [Scaling Laws for Neural Language Models](/foundations/courses-and-learning-paths/scaling-laws-for-neural-language-models/index.md) Creator not supplied; see original source. arXiv paper (2020) "Scaling Laws for Neural Language Models", measuring power-law scaling of language model loss with size, data and compute. Advanced · unknown · unknown resource · en - ### [scvi-tools](/foundations/courses-and-learning-paths/scvi-tools/index.md) Creator not supplied; see original source. scvi-tools: library of probabilistic deep generative models for single-cell omics data. Advanced · unknown · unknown resource · en - ### [Switch Transformers](/foundations/courses-and-learning-paths/switch-transformers/index.md) Creator not supplied; see original source. arXiv paper (2021) introducing Switch Transformers, sparse mixture-of-experts models scaled to a trillion parameters. Advanced · unknown · unknown resource · en - ### [A decoder-only foundation model for time-series forecasting (TimesFM)](/foundations/llm-fundamentals/timesfm-2/index.md) Creator not supplied; see original source. arXiv paper (2023) introducing TimesFM, a decoder-only foundation model for time-series forecasting. Advanced–Expert · unknown · unknown resource · en - ### [tslearn](/foundations/llm-fundamentals/tslearn/index.md) Creator not supplied; see original source. tslearn documentation: Python machine learning tools for time-series analysis. Advanced · unknown · unknown resource · en - ### [U-Net](/foundations/llm-fundamentals/u-net/index.md) Creator not supplied; see original source. arXiv paper (2015) "U-Net: Convolutional Networks for Biomedical Image Segmentation", introducing the encoder-decoder architecture with skip connections. Advanced–Expert · unknown · unknown resource · en - ### [Umar Jamil (YouTube)](/foundations/practitioner-overviews/umar-jamil-handle-unconfirmed/index.md) Creator not supplied; see original source. Umar Jamil's YouTube channel: line-by-line implementations of Transformer, LLaMA and diffusion models. Advanced · unknown · unknown resource · en - ### [verifiers v1](/foundations/llm-fundamentals/verifiers-v1/index.md) Creator not supplied; see original source. Prime Intellect post on verifiers v1, splitting environments into tasksets, harnesses and runtimes for agentic RL and evals. Advanced · unknown · unknown resource · en - ### [VGG](/foundations/llm-fundamentals/vgg/index.md) Creator not supplied; see original source. arXiv PDF of the VGG paper (2014) on very deep convolutional networks for large-scale image recognition. Advanced–Expert · unknown · unknown resource · und - ### [ViT](/foundations/llm-fundamentals/vit/index.md) Creator not supplied; see original source. arXiv paper (2020) introducing the Vision Transformer (ViT) for image recognition. Advanced–Expert · unknown · unknown resource · en - ### [WaveNet](/foundations/llm-fundamentals/wavenet/index.md) Creator not supplied; see original source. arXiv paper (2016) "WaveNet: A Generative Model for Raw Audio", introducing WaveNet, an autoregressive generative model of raw audio. Advanced–Expert · unknown · unknown resource · en - ### [Wide & Deep](/foundations/llm-fundamentals/wide-deep/index.md) Creator not supplied; see original source. arXiv paper (2016) "Wide & Deep Learning for Recommender Systems", introducing Google's Wide & Deep recommender model. Advanced–Expert · unknown · unknown resource · en - ### [xLSTM (NXAI, Linz)](/foundations/llm-fundamentals/xlstm-nxai-linz/index.md) Creator not supplied; see original source. arXiv paper (2024) introducing xLSTM, extended long short-term memory with exponential gating and matrix memory. Advanced–Expert · unknown · unknown resource · en - ### [YOLO](/foundations/llm-fundamentals/yolo/index.md) Creator not supplied; see original source. arXiv paper (2015) "You Only Look Once: Unified, Real-Time Object Detection", introducing YOLO, a single-stage real-time object detector. Advanced · unknown · unknown resource · en - ### [AWQ](/foundations/courses-and-learning-paths/awq/index.md) Creator not supplied; see original source. arXiv paper (2023) introducing AWQ, activation-aware weight quantization for LLM compression. Expert · unknown · unknown resource · en - ### [EASA AI Concept Paper Proposed Issue 03](/foundations/llm-fundamentals/easa-ai-concept-paper-proposed-issue-03/index.md) Creator not supplied; see original source. EASA AI Concept Paper Proposed Issue 03 (PDF), extending aviation AI assurance guidance to more methods and Level 3 automation. Expert · unknown · unknown resource · en - ### [ELIS 2025 report (European Language Industry Survey)](/foundations/courses-and-learning-paths/elis-2025-report-european-language-industry-survey/index.md) Creator not supplied; see original source. European Language Industry Survey 2025 report (PDF) on trends, including AI, in the translation industry. Expert · unknown · unknown resource · en - ### [GPTQ](/foundations/courses-and-learning-paths/gptq/index.md) Creator not supplied; see original source. arXiv paper (2022) introducing GPTQ, accurate post-training weight quantization for generative transformers. Expert · unknown · unknown resource · en - ### [HBS: Navigating the Jagged Technological Frontier (BCG study)](/foundations/courses-and-learning-paths/hbs-navigating-the-jagged-technological-frontier-bcg-study/index.md) Creator not supplied; see original source. Harvard Business School working paper Navigating the Jagged Technological Frontier: field experiment with BCG consultants using GPT-4. Expert · unknown · unknown resource · en - ### [Reward Hacking in Reinforcement Learning (Lil'Log)](/foundations/llm-fundamentals/lilian-weng-reward-hacking-in-rl/index.md) Creator not supplied; see original source. Lilian Weng's survey of reward hacking in reinforcement learning, including in RLHF and coding tasks. Expert · unknown · unknown resource · en - ### [Machine Learning Street Talk (YouTube)](/foundations/practitioner-overviews/machine-learning-street-talk-tim-scarfe-handle-unconfirmed/index.md) Creator not supplied; see original source. Machine Learning Street Talk YouTube channel: long interviews and debates with AI researchers. Expert · unknown · unknown resource · en - ### [Mamba](/foundations/llm-fundamentals/mamba/index.md) Creator not supplied; see original source. arXiv paper (2023) introducing Mamba, linear-time sequence modelling with selective state spaces. Expert · unknown · unknown resource · en - ### [Mem0 paper](/foundations/courses-and-learning-paths/mem0-paper/index.md) Creator not supplied; see original source. arXiv paper (2025) introducing Mem0, scalable long-term memory for production AI agents, with benchmarks. Expert · unknown · unknown resource · en - ### [Olmo 3 technical report](/foundations/courses-and-learning-paths/olmo-3-technical-report/index.md) Creator not supplied; see original source. arXiv paper (2025) Olmo 3 technical report on Ai2's fully open 7B and 32B models. Expert · unknown · unknown resource · en - ### [Smol Training Playbook (Hugging Face Space)](/foundations/courses-and-learning-paths/smol-training-playbook-hf/index.md) Creator not supplied; see original source. Hugging Face Smol Training Playbook: end-to-end account of training the SmolLM3 model, including failures and decisions. Expert · unknown · unknown resource · en [Previous page](/foundations/page/21/index.md) [Next page](/foundations/page/23/index.md) [Plain-text Markdown copy](/foundations/page/22/index.md)