https://magazine.sebastianraschka.com/p/building-llms-from-the-ground-up
https://magazine.sebastianraschka.com/p/understanding-reasoning-llms
https://magazine.sebastianraschka.com/i/148329414/references
https://magazine.sebastianraschka.com/p/understanding-and-coding-self-attention
https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison
https://magazine.sebastianraschka.com/p/llm-training-rlhf-and-its-alternatives
https://magazine.sebastianraschka.com/i/156484949/thoughts-about-deepseek-r1
https://magazine.sebastianraschka.com/i/156484949/the-4-main-ways-to-build-and-improve-reasoning-models
https://magazine.sebastianraschka.com/i/156484949/developing-reasoning-models-on-a-limited-budget
https://magazine.sebastianraschka.com/i/156484949/conclusion
https://magazine.sebastianraschka.com/i/156484949/2-pure-reinforcement-learning-rl
https://magazine.sebastianraschka.com/i/156484949/a-brief-look-at-the-deepseek-training-pipeline
https://magazine.sebastianraschka.com/i/156484949/4-pure-supervised-finetuning-sft-and-distillation
https://magazine.sebastianraschka.com/p/ai-research-papers-2024-part-2
https://magazine.sebastianraschka.com/i/156484949/how-do-we-define-reasoning-model
https://magazine.sebastianraschka.com/i/156484949/3-supervised-finetuning-and-reinforcement-learning-sft-rl
https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms
https://magazine.sebastianraschka.com/i/156484949/when-should-we-use-reasoning-models
https://magazine.sebastianraschka.com/i/156484949/1-inference-time-scaling
https://magazine.sebastianraschka.com/i/140464659/embedding-an-input-sentence
https://magazine.sebastianraschka.com/i/140464659/self-attention
https://magazine.sebastianraschka.com/i/140464659/computing-the-attention-weights
https://magazine.sebastianraschka.com/i/140464659/defining-the-weight-matrices
https://magazine.sebastianraschka.com/i/140464659/causal-self-attention
https://magazine.sebastianraschka.com/i/140464659/multi-head-attention
https://magazine.sebastianraschka.com/i/140464659/introducing-self-attention
https://magazine.sebastianraschka.com/i/140464659/computing-the-unnormalized-attention-weights
https://magazine.sebastianraschka.com/i/140464659/conclusion
https://magazine.sebastianraschka.com/i/140464659/bonus-topic-cross-attention
https://magazine.sebastianraschka.com/p/llms-building-training-finetuning
https://magazine.sebastianraschka.com/p/coding-llms-from-the-ground-up
https://magazine.sebastianraschka.com/i/162934205/7-instruction-finetuning-14604
https://magazine.sebastianraschka.com/i/162934205/1-set-up-your-code-environment-02101
https://magazine.sebastianraschka.com/i/162934205/4-set-up-your-code-environment-02101
https://magazine.sebastianraschka.com/i/162934205/bonus-llms-then-and-now-from-2018-to-2025
https://magazine.sebastianraschka.com/i/162934205/2-working-with-text-data-12801
https://magazine.sebastianraschka.com/i/162934205/references
https://magazine.sebastianraschka.com/i/162934205/5-pretraining-on-unlabeled-data-23644
https://magazine.sebastianraschka.com/i/162934205/6-finetuning-for-classification-21529
https://magazine.sebastianraschka.com/i/162934205/3-coding-attention-mechanisms-21540
https://magazine.sebastianraschka.com/i/162934205/
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week
https://nlp.elvissaravia.com/i/158106009/7-a-multi-agent-framework-for-chart-generation
https://nlp.elvissaravia.com/i/158106009/8-lightthinker
https://nlp.elvissaravia.com/p/recursive-language-models-stop-stuffing
https://nlp.elvissaravia.com/p/ai-agents-weekly-agentic-reasoning
https://nlp.elvissaravia.com/i/158106009/4-emergent-misalignment
https://nlp.elvissaravia.com/i/158106009/9-a-systematic-survey-of-prompt-optimization
https://nlp.elvissaravia.com/p/context-engineering-guide
https://nlp.elvissaravia.com/i/158106009/5-an-efficient-alternative-to-self-attention
https://nlp.elvissaravia.com/i/158106009/6-plangen
https://nlp.elvissaravia.com/i/158106009/3-chain-of-draft
https://nlp.elvissaravia.com/i/158106009/10-protein-llms
https://nlp.elvissaravia.com/i/158106009/2-gpt-45
https://nlp.elvissaravia.com/i/158106009/1-claude-37-sonnet
https://nlp.elvissaravia.com/i/187783349/final-words-and-resources
https://nlp.elvissaravia.com/i/187783349/the-results
https://nlp.elvissaravia.com/i/187783349/the-model-is-a-programmer-not-a-reader
https://nlp.elvissaravia.com/i/187783349/current-limitations-worth-being-honest-about
https://nlp.elvissaravia.com/i/187783349/what-the-model-actually-does
https://nlp.elvissaravia.com/p/ai-agents-weekly-claude-opus-45-omniscientist
https://nlp.elvissaravia.com/i/187783349/what-makes-this-interesting-for-the-future
https://nlp.elvissaravia.com/i/187783349/the-problem-context-rot
https://nlp.elvissaravia.com/i/187783349/but-isnt-this-just
https://nlp.elvissaravia.com/i/185586518/agentic-reasoning-for-llms
https://nlp.elvissaravia.com/i/185586518/top-stories
https://nlp.elvissaravia.com/i/185586518/unrolling-the-codex-agent-loop
https://nlp.elvissaravia.com/p/ai-agents-weekly
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-bca
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-0ac
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-cc2
https://nlp.elvissaravia.com/p/ai-agents-weekly-openai-agents-api
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-374
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-9b0
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-956
https://nlp.elvissaravia.com/p/ai-agents-weekly-kimi-k3-thinking
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-16b
https://nlp.elvissaravia.com/p/ai-agents-weekly-jev-salesforce-koa
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-4f3
https://nlp.elvissaravia.com/p/ai-agents-weekly-kimi-k3-deepseek
https://nlp.elvissaravia.com/t/ai-agents
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-878
https://nlp.elvissaravia.com/p/ai-agents-weekly-glm-53-flash-hy4
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-ca0
https://nlp.elvissaravia.com/p/ai-agents-weekly-gemini-4-argon-openai
https://nlp.elvissaravia.com/p/ai-agents-weekly-deepseek-harness
https://nlp.elvissaravia.com/p/ai-agents-weekly-agent-plugins-standard
https://nlp.elvissaravia.com/p/ai-agents-weekly-claude-opus-55-gpt
https://nlp.elvissaravia.com/p/ai-agents-weekly-claude-opus-5-openai
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-ef5
https://nlp.elvissaravia.com/t/ai
https://nlp.elvissaravia.com/p/ai-agents-weekly-nvidia-avo-trueforge
https://nlp.elvissaravia.com/p/top-ai-papers-of-the-week-6e2
https://nlp.elvissaravia.com/t/ai-devs
https://nlp.elvissaravia.com/p/ai-agents-weekly-gpt-6-astra-claude
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/UDA-image-results.png
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#pseudo-labeling-with-consistency-regularization
https://lilianweng.github.io/posts/2021-05-31-contrastive/
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#references
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/mean-teacher.png
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#mean-teachers
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#consistency-regularization
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/PI-model.png
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#notations
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/mean-teacher-results.png
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#label-propagation
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/ICT.png
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/MixMatch.png
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/FixMatch-results.png
https://lilianweng.github.io/tags/unsupervised-learning/
https://lilianweng.github.io/posts/2021-05-31-contrastive/#simclr
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#fixmatch
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#temporal-ensembling
https://lilianweng.github.io/posts/2021-12-05-semi-supervised/#top
https://lilianweng.github.io/posts/2021-09-25-train-large/
https://lilianweng.github.io/posts/2019-01-31-lm/