https://magazine.sebastianraschka.com/archivedailyhttps://magazine.sebastianraschka.com/aboutweeklyhttps://magazine.sebastianraschka.com/p/visual-attention-variants2026-03-22monthlyhttps://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight2026-03-07monthlyhttps://magazine.sebastianraschka.com/p/categories-of-inference-time-scaling2026-01-24monthlyhttps://magazine.sebastianraschka.com/p/state-of-llms-20252026-01-20monthlyhttps://magazine.sebastianraschka.com/p/llm-research-papers-2025-part22026-01-01monthlyhttps://magazine.sebastianraschka.com/p/technical-deepseek2026-01-01monthlyhttps://magazine.sebastianraschka.com/p/beyond-standard-llms2026-02-21monthlyhttps://magazine.sebastianraschka.com/p/llm-evaluation-4-approaches2025-10-10monthlyhttps://magazine.sebastianraschka.com/p/qwen3-from-scratch2025-12-22monthlyhttps://magazine.sebastianraschka.com/p/from-gpt-2-to-gpt-oss-analyzing-the2025-08-15monthlyhttps://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison2026-04-03monthlyhttps://magazine.sebastianraschka.com/p/llm-research-papers-2025-list-one2025-07-01monthlyhttps://magazine.sebastianraschka.com/p/coding-the-kv-cache-in-llms2025-11-24monthlyhttps://magazine.sebastianraschka.com/p/coding-llms-from-the-ground-up2025-06-16monthlyhttps://magazine.sebastianraschka.com/p/the-state-of-llm-reasoning-model-training2026-01-24monthlyhttps://magazine.sebastianraschka.com/p/first-look-at-reasoning-from-scratch2025-06-09monthlyhttps://magazine.sebastianraschka.com/p/state-of-llm-reasoning-and-inference-scaling2025-04-17monthlyhttps://magazine.sebastianraschka.com/p/understanding-reasoning-llms2026-01-29monthlyhttps://magazine.sebastianraschka.com/p/ai-research-papers-2024-part-22025-01-16monthlyhttps://magazine.sebastianraschka.com/p/ai-research-papers-2024-part-12025-02-27monthlyhttps://magazine.sebastianraschka.com/p/llm-research-papers-the-2024-list2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/understanding-multimodal-llms2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/building-a-gpt-style-llm-classifier2025-03-08monthlyhttps://magazine.sebastianraschka.com/p/building-llms-from-the-ground-up2024-12-21monthlyhttps://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/instruction-pretraining-llms2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/llms-building-training-finetuning2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/llm-research-insights-instruction2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/how-good-are-the-latest-open-llms2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/using-and-finetuning-pretrained-transformers2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/tips-for-llm-pretraining-and-evaluating-rms2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/research-papers-in-february-20242025-02-09monthlyhttps://magazine.sebastianraschka.com/p/lora-and-dora-from-scratch2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/supporting-ahead-of-ai2025-08-29monthlyhttps://magazine.sebastianraschka.com/p/research-papers-in-january-20242025-02-09monthlyhttps://magazine.sebastianraschka.com/p/understanding-and-coding-self-attention2026-03-09monthlyhttps://magazine.sebastianraschka.com/p/10-ai-research-papers-20232025-02-09monthlyhttps://magazine.sebastianraschka.com/p/research-papers-in-november-20232024-08-12monthlyhttps://magazine.sebastianraschka.com/p/practical-tips-for-finetuning-llms2025-02-09monthlyhttps://magazine.sebastianraschka.com/p/research-papers-october-20232024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ai-and-open-source-in-20232024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-12-llm-businesses2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/research-highlights-in-three-sentences-3d52024-08-12monthlyhttps://magazine.sebastianraschka.com/p/llm-training-rlhf-and-its-alternatives2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/the-missing-bits-llama-2-weights2025-03-07monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-11-new-foundation-models2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/research-highlights-in-three-sentences2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/large-language-models-and-nearest2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ai-research-highlights-in-3-sentences-7382024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-10-state-of-computer2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/accelerating-pytorch-model-training2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/understanding-encoder-and-decoder2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ai-research-highlights-in-3-sentences-2a12024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-9-llm-tuning-and-dataset2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/why-the-original-transformer-figure2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/finetuning-llms-with-adapters2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ai-research-highlights-in-3-sentences2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-8-the-latest-open-source2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/understanding-parameter-efficient2025-03-07monthlyhttps://magazine.sebastianraschka.com/p/finetuning-large-language-models2025-03-07monthlyhttps://magazine.sebastianraschka.com/p/understanding-large-language-models2024-12-22monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-7-large-language-models2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-6-train-differently2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-5-revaival-of-ideas2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-4-a-big-year-for-ai2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-3-ainnouncements2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-2-transformers-fast-and2024-08-12monthlyhttps://magazine.sebastianraschka.com/p/ahead-of-ai-1-a-diffusion-of-innovations2024-08-12monthly