https://layernorm.dev/CLAUDE.html 2026-03-01T04:16:11.721Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/61-revaival-of-ideas-from-next-generation-convolutional-neural-.html 2026-03-01T04:16:12.172Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/21-building-a-gpt-style-llm-classifier-from-scratch.html 2026-03-01T04:16:12.166Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/52-about-layernorm-variants-in-the-original-transformer-paper-a.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/16-understanding-reasoning-llms.html 2026-03-01T04:16:12.165Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/01-categories-of-inference-time-scaling-for-improved-llm-reason.html 2026-03-01T04:16:12.162Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/34-ten-noteworthy-ai-research-papers-of-2023.html 2026-03-01T04:16:12.168Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/20-understanding-multimodal-llms.html 2026-03-01T04:16:12.166Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/23-new-llm-pre-training-and-post-training-paradigms.html 2026-03-01T04:16:12.166Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/26-llm-research-insights-instruction-masking-and-new-lora-finet.html 2026-03-01T04:16:12.167Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/35-tackling-hallucinations-boosting-reasoning-abilities-and-new.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/50-direct-preference-optimization-for-human-feedback-and-more.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/37-a-potential-successor-to-rlhf-for-efficient-llm-alignment-an.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/40-from-self-alignment-to-longlora.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/13-the-state-of-reinforcement-learning-for-llm-reasoning.html 2026-03-01T04:16:12.165Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/46-long-contexts-and-scaling-transformers-to-1-000-000-000-toke.html 2026-03-01T04:16:12.170Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/47-state-of-computer-vision-2023-from-vision-transformers-to-ne.html 2026-03-01T04:16:12.170Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/29-tips-for-llm-pretraining-and-evaluating-reward-models.html 2026-03-01T04:16:12.167Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/19-llm-research-papers-the-2024-list.html 2026-03-01T04:16:12.166Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/31-improving-lora-implementing-weight-decomposed-low-rank-adapt.html 2026-03-01T04:16:12.168Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/18-noteworthy-ai-research-papers-of-2024-part-one.html 2026-03-01T04:16:12.165Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/03-llm-research-papers-the-2025-list-july-to-december.html 2026-03-01T04:16:12.163Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/07-understanding-and-implementing-qwen3-from-scratch.html 2026-03-01T04:16:12.164Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/index.html 2026-03-01T04:16:12.173Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/56-understanding-parameter-efficient-llm-finetuning-prompt-tuni.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/45-large-language-models-and-nearest-neighbors.html 2026-03-01T04:16:12.170Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/10-llm-research-papers-the-2025-list-january-to-june.html 2026-03-01T04:16:12.164Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/02-the-state-of-llms-2025-progress-problems-and-predictions.html 2026-03-01T04:16:12.162Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/33-understanding-and-coding-self-attention-multi-head-attention.html 2026-03-01T04:16:12.168Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/38-ai-and-open-source-in-2023.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/36-practical-tips-for-finetuning-llms-using-lora-low-rank-adapt.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/12-coding-llms-from-the-ground-up-a-complete-course.html 2026-03-01T04:16:12.164Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/39-llm-business-and-busyness-recent-company-investments-and-ai-.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/17-noteworthy-ai-research-papers-of-2024-part-two.html 2026-03-01T04:16:12.165Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/27-how-good-are-the-latest-open-llms-and-is-dpo-better-than-ppo.html 2026-03-01T04:16:12.167Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/06-understanding-the-4-main-approaches-to-llm-evaluation-from-s.html 2026-03-01T04:16:12.163Z https://layernorm.dev/posts/old_blogs/2012-05-24-dfsid迭代加深搜索/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2011-11-03-环问题处理方法/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2012-12-22-usaco-4-2-ditch/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2012-01-23-bfs如何记录路径/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2011-12-05-如果你是acmer你会选择哪个职业【转自某大牛博客】/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2010-08-18-取石子问题-2/index.html 2026-03-01T04:16:11.897Z https://layernorm.dev/posts/old_blogs/2015-01-07-round-283-div-2-e-distributing-parts/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2011-10-12-2007问题求解2/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2011-11-08-usaco-s1-3-mixing-milk-贪心证明/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2012-05-21-扩展欧几里得算法/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2012-05-21-二元一次不定方程通解公式推导/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2012-08-14-网络流的一些个人证明/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2011-10-24-tarjan的理解/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2012-05-21-gcdnn11-证明/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2012-06-03-算法导论第26章网络流-引理26-1证明/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2011-11-25-【转】sstream数字与字符串相互转换/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2010-12-09-最长不下降子序列注意问题/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2011-11-28-usaco第一章刷完！/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2012-05-17-数论相关定理及证明/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2012-01-18-abgcdablcmab证明/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2012-05-26-usaco-4-1-fence-rails题解/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2015-03-22-binary-raise-algorithm/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2012-01-29-诗【无题】/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2013-08-26-udacity-cs255-finally-made-it-through/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2011-10-21-弗洛伊德求最小环算法/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2011-11-26-usaco上看到一个极妙的分数01排序。/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2012-06-28-算法导论-edmonds-karp算法时间复杂度证明/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2015-01-06-round-283-div-2-d-tennis-game/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2012-05-22-usaco-4-1-beef-mcnuggets-dp上界证明/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2012-02-08-任意二维多边形面积/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2010-12-01-采药-tyvj-p1005/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2011-10-17-贪心证明法：交换参数/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2015-01-26-codeforces-round-286-div-2-d-mr-kitayutas-technology/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2014-12-21-beta-round-1-c-ancient-berland-circus/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2012-02-01-欧拉路径错误原因研究/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2011-09-23-最大和连续子序列问题/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2012-12-27-usaco-4-2-job-processing-analysis/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2015-03-08-some-notes-about-unconstrained-otptimization/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2015-02-11-backpropagation-derivation/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2012-05-20-纪念在深圳打得第一场也应该是最后一场比赛/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2011-11-17-写了个生命游戏，无聊做下数据统计。/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2011-10-21-spfa及其优化/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2012-04-22-对于在vector中-当前迭代器在末尾时-使用pop_back出错解决方/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2010-12-27-henry拣钱money-pasccpp/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2010-12-24-新年趣事之打牌/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2015-03-26-a-nice-trick-for-computing-modular-multiplicative-inverses-for-first-n-consecutive-numbers-in-linear-time/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2013-10-25-explanation-of-the-binary-shift-method-for-josephus-problem/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2011-09-22-15届noip初赛问题求解2/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/welcome/index.html 2026-03-01T04:16:12.160Z https://layernorm.dev/posts/robotics/5-neuro-inspired-architectures/index.html 2026-03-01T04:16:12.026Z https://layernorm.dev/posts/robotics/state-of-robotics-2026/index.html 2026-03-01T04:16:12.114Z https://layernorm.dev/posts/robotics/7-neural-manifolds/index.html 2026-03-01T04:16:12.032Z https://layernorm.dev/posts/robotics/1-diffusion-policy/index.html 2026-03-01T04:16:11.919Z https://layernorm.dev/posts/robotics/2-much-ado-about-noising/index.html 2026-03-01T04:16:12.010Z https://layernorm.dev/posts/robotics/1-background/index.html 2026-03-01T04:16:11.907Z https://layernorm.dev/posts/diffusion/10-diffusion-transformers/index.html 2026-03-01T04:16:11.828Z https://layernorm.dev/posts/diffusion/6-score-functions/index.html 2026-03-01T04:16:11.869Z https://layernorm.dev/posts/diffusion/12-why-diffusion/index.html 2026-03-01T04:16:11.845Z https://layernorm.dev/posts/diffusion/1-intro/index.html 2026-03-01T04:16:11.825Z https://layernorm.dev/posts/diffusion/7-training/index.html 2026-03-01T04:16:11.876Z https://layernorm.dev/posts/diffusion/8-guidance/index.html 2026-03-01T04:16:11.881Z https://layernorm.dev/index.html 2026-03-01T04:16:11.824Z https://layernorm.dev/posts/diffusion/5-diffusion-sde/index.html 2026-03-01T04:16:11.866Z https://layernorm.dev/posts/diffusion/2-flows/index.html 2026-03-01T04:16:11.853Z https://layernorm.dev/posts/diffusion/3-probability-paths/index.html 2026-03-01T04:16:11.861Z https://layernorm.dev/posts/diffusion/11-practical-flow-matching/index.html 2026-03-01T04:16:11.832Z https://layernorm.dev/posts/diffusion/4-flow-matching-loss/index.html 2026-03-01T04:16:11.866Z https://layernorm.dev/posts/diffusion/9-unet/index.html 2026-03-01T04:16:11.882Z https://layernorm.dev/posts/robotics/6-eigenvalue-dynamics/index.html 2026-03-01T04:16:12.030Z https://layernorm.dev/posts/robotics/linoss/index.html 2026-03-01T04:16:12.058Z https://layernorm.dev/posts/robotics/1.5-action-chunking/index.html 2026-03-01T04:16:12.007Z https://layernorm.dev/posts/robotics/0-intro/index.html 2026-03-01T04:16:11.905Z https://layernorm.dev/posts/robotics/3-vla-models/index.html 2026-03-01T04:16:12.017Z https://layernorm.dev/posts/robotics/libero-benchmark/index.html 2026-03-01T04:16:12.032Z https://layernorm.dev/posts/old_blogs/2012-02-08-向量的向量积/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2010-11-29-ski/index.html 2026-03-01T04:16:11.897Z https://layernorm.dev/posts/old_blogs/2010-11-22-最大公约数和最小公倍数问题/index.html 2026-03-01T04:16:11.897Z https://layernorm.dev/posts/old_blogs/2012-01-12-组合数快速算法【转载】/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2011-10-11-比较法排序为何能以最少的对换次数完成证明/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2012-04-17-计算几何-线段相交/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2012-01-15-一个圆盘，旋转速度为v度，360个时间单位后必回到/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2010-12-13-石子合并注意地方。/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2011-10-31-229/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2011-12-10-史上最无语的冷笑话。。。【转载】/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2011-11-03-usacomilk2-个人题解/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2015-02-06-solution-for-the-critical-isotherm-from-van-der-waals-equation/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2015-03-19-srm-653-div-1/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2015-03-25-weird-mod-behaviour-when-using-define/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2011-09-09-完全二叉树-fpcp2证明/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2012-07-05-压入与重标记算法中不存在顶点v∈v-st且hvhs证明/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2011-10-28-位运算相关【转载】/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2011-11-08-usaco-s1-3-barn-repair-贪心证明/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2012-05-22-两个互质的数ab，axbyxyab≥0）最大不能表示为ab-a-b证明/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2011-10-12-2007问题求解1/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2010-12-27-挖地雷问题/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2011-09-09-终于想明白为什么单调队列因入队而删掉的元素不/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2014-04-24-first-time-writing-segment-tree/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2012-01-09-今天看了下11年acm的队名，我彻底无语了。。。。。/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2011-11-01-二份答案需注意的细节问题/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2015-01-16-conversion-between-factorial-number-system-and-permutations/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2012-05-21-素数无穷性的证明/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2011-10-21-链式前向星【转帖】/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2011-12-11-在一个有限的范围内，若干个物体以各自的规则移/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2012-01-30-dijkstra的堆优化时间复杂度【转载】/index.html 2026-03-01T04:16:11.901Z https://layernorm.dev/posts/old_blogs/2010-11-23-带完成/index.html 2026-03-01T04:16:11.897Z https://layernorm.dev/posts/old_blogs/2015-01-08-round-282-div-2-c-treasure/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2013-12-19-proof-of-perfect-squares-have-an-odd-number-of-factors/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2012-07-15-最大流最小割定理个人理解/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2013-11-21-proof-of-evenshtein-distance/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2013-11-08-got-in-top-11-in-uva-problem-143-orchard-trees/index.html 2026-03-01T04:16:11.903Z https://layernorm.dev/posts/old_blogs/2011-11-12-回文词细节问题/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2015-03-28-srm-653-div-1-2/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2011-11-04-思路启示/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2010-12-02-115/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2012-01-02-在这吐槽下，usaco输出格式真是欠扁。。。！/index.html 2026-03-01T04:16:11.900Z https://layernorm.dev/posts/old_blogs/2010-11-23-数的计数/index.html 2026-03-01T04:16:11.897Z https://layernorm.dev/posts/old_blogs/2011-09-21-15届noip提高组初赛问题求解1/index.html 2026-03-01T04:16:11.898Z https://layernorm.dev/posts/old_blogs/2015-03-11-zoutendijks-condition/index.html 2026-03-01T04:16:11.904Z https://layernorm.dev/posts/old_blogs/2012-05-21-裴蜀定理/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/posts/old_blogs/2011-11-10-c文件读入所有字符（空格，换行符。。。）方法/index.html 2026-03-01T04:16:11.899Z https://layernorm.dev/posts/old_blogs/2010-12-01-01背包注意事项（重要）/index.html 2026-03-01T04:16:11.897Z https://layernorm.dev/posts/old_blogs/2012-12-23-an-important-proof-of-hungarian-algorithm/index.html 2026-03-01T04:16:11.902Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/01-the-big-llm-architecture-comparison.html 2026-03-01T04:16:12.162Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/41-llm-training-rlhf-and-its-alternatives.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/59-large-language-models-3-0.html 2026-03-01T04:16:12.172Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/51-llm-tuning-dataset-perspectives.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/44-llama-2-flash-attention-2-and-more.html 2026-03-01T04:16:12.170Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/60-train-differently-do-we-need-reinforcement-learning-with-hum.html 2026-03-01T04:16:12.172Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/03-state-of-llms-2025.html 2026-03-01T04:16:12.163Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/65-a-diffusion-of-innovations-recent-developments-in-generative.html 2026-03-01T04:16:12.173Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/22-building-llms-from-the-ground-up-a-3-hour-coding-workshop.html 2026-03-01T04:16:12.166Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/02-understanding-reasoning-llms.html 2026-03-01T04:16:12.162Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/54-transformers-for-long-inputs-and-less-training-data.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/30-a-lora-successor-small-finetuned-llms-vs-generalist-llms-and.html 2026-03-01T04:16:12.168Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/64-transformers-fast-and-slow-new-developments-in-language-proc.html 2026-03-01T04:16:12.172Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/11-understanding-and-coding-the-kv-cache-in-llms-from-scratch.html 2026-03-01T04:16:12.164Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/32-model-merging-mixtures-of-experts-and-towards-smaller-llms.html 2026-03-01T04:16:12.168Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/58-understanding-large-language-models.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/62-looking-back-at-2022-a-big-year-for-ai.html 2026-03-01T04:16:12.172Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/48-accelerating-pytorch-model-training.html 2026-03-01T04:16:12.170Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/55-insights-from-large-scale-llm-training-runs.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/05-beyond-standard-llms.html 2026-03-01T04:16:12.163Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/43-new-foundation-models-codellama-and-other-highlights-in-open.html 2026-03-01T04:16:12.170Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/49-understanding-encoder-and-decoder-llms.html 2026-03-01T04:16:12.170Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/25-developing-an-llm-building-training-finetuning.html 2026-03-01T04:16:12.167Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/53-finetuning-llms-efficiently-with-adapters.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/42-the-missing-bits-llama-2-weights-have-changed.html 2026-03-01T04:16:12.169Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/14-first-look-at-reasoning-from-scratch-chapter-1.html 2026-03-01T04:16:12.165Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/15-the-state-of-llm-reasoning-model-inference.html 2026-03-01T04:16:12.165Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/04-from-deepseek-v3-to-v3-2-architecture-sparse-attention-and-r.html 2026-03-01T04:16:12.163Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/09-the-big-llm-architecture-comparison.html 2026-03-01T04:16:12.164Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/08-from-gpt-2-to-gpt-oss-analyzing-the-architectural-advances.html 2026-03-01T04:16:12.164Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/24-instruction-pretraining-llms.html 2026-03-01T04:16:12.167Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/63-launching-large-language-models-and-open-source-software.html 2026-03-01T04:16:12.172Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/57-finetuning-large-language-models.html 2026-03-01T04:16:12.171Z https://layernorm.dev/research/ahead-of-ai-analysis/raw/28-using-and-finetuning-pretrained-transformers.html 2026-03-01T04:16:12.167Z https://layernorm.dev/about.html 2026-03-01T04:16:11.721Z