<![CDATA[Aryan]]>https://www.aryanupadhyay.com/blogRSS for NodeThu, 13 Aug 2026 06:47:43 GMT<![CDATA[Transformer Inference Explained: A Step-by-Step Guide to Autoregressive Decoding]]>https://www.aryanupadhyay.tech/post/transformer-inference-step-by-step697da4e12b413b3ab9da59fdThu, 19 Mar 2026 05:37:42 GMTAryan<![CDATA[The Transformer Decoder Explained: Architecture, Math & Operations]]>https://www.aryanupadhyay.tech/post/transformer-decoder-architecture-deep-dive697b7250facc7df23b58e341Sun, 15 Mar 2026 06:03:11 GMTAryan<![CDATA[Cross Attention in Transformers Explained: Self vs Cross Attention Step by Step]]>https://www.aryanupadhyay.tech/post/cross-attention-in-transformers-explained697b69b5c1bd63f263ff710aThu, 12 Mar 2026 01:52:18 GMTAryan<![CDATA[Masked Self Attention Explained: Why Transformers Are Autoregressive Only at Inference]]>https://www.aryanupadhyay.tech/post/masked-self-attention-transformer-autoregressive697ac96930ffdbbf2ba1528eTue, 10 Mar 2026 02:55:08 GMTAryan<![CDATA[Transformer Encoder Architecture Explained Step by Step (With Intuition)]]>https://www.aryanupadhyay.tech/post/transformer-encoder-architecture-explained6978a2744d2d07064e19e760Sun, 08 Mar 2026 01:38:58 GMTAryan<![CDATA[Layer Normalization Explained: Why Transformers Prefer It Over Batch Norm]]>https://www.aryanupadhyay.tech/post/layer-normalisation-in-transformers69777336d87a588901624782Fri, 06 Mar 2026 03:06:53 GMTAryan<![CDATA[Positional Encoding in Transformers Explained from First Principles]]>https://www.aryanupadhyay.tech/post/positional-encoding-in-transformers-explained-from-first-principles697632829c4baa18ad9781f0Wed, 04 Mar 2026 04:42:50 GMTAryan<![CDATA[Multi-Head Attention in Transformers Explained: Concepts, Math & Mechanics]]>https://www.aryanupadhyay.tech/post/multi-head-attention-in-transformers-explained-concepts-math-mechanics6974a041e389f5384b709a45Mon, 02 Mar 2026 04:16:38 GMTAryan<![CDATA[Why Is Self-Attention Called “Self”? Understanding Attention Mechanisms from Encoder–Decoder to Transformers]]>https://www.aryanupadhyay.tech/post/why-is-self-attention-called-self-understanding-attention-mechanisms-from-encoder-decoder-to-tran697394ccaa29322cefcc1385Sat, 28 Feb 2026 04:59:14 GMTAryan<![CDATA[The Evolution of Object Detection: Fast R-CNN and Faster R-CNN Explained]]>https://www.aryanupadhyay.tech/post/evolution-fast-and-faster-rcnn-object-detection69a154ecfa78e209eb8a8a90Fri, 27 Feb 2026 08:40:44 GMTAryan<![CDATA[Visualizing Self-Attention: A Geometric Intuition & The Math Behind the Magic]]>https://www.aryanupadhyay.tech/post/visualizing-self-attention-a-geometric-intuition-the-math-behind-the-magic6973912016ee2e0564598964Thu, 26 Feb 2026 08:13:17 GMTAryan<![CDATA[R-CNN Explained: A Comprehensive Guide to Object Detection Architecture]]>https://www.aryanupadhyay.tech/post/rcnn-object-detection-guide699d5fa29509a0da66f938fcTue, 24 Feb 2026 08:44:35 GMTAryan<![CDATA[Scaled Dot-Product Attention Explained: Why We Divide by √dₖ in Transformers]]>https://www.aryanupadhyay.tech/post/scaled-dot-product-attention-explained-why-we-divide-by-d%E2%82%96-in-transformers69733a0c073d167beebadf36Sat, 21 Feb 2026 11:19:46 GMTAryan<![CDATA[Self-Attention in Transformers Explained from First Principles (With Intuition & Math)]]>https://www.aryanupadhyay.tech/post/self-attention-in-transformers-explained-from-first-principles-with-intuition-math69722759affc20191ac0c0d0Thu, 19 Feb 2026 12:50:51 GMTAryan<![CDATA[Bahdanau vs. Luong Attention: Architecture, Math, and Differences Explained]]>https://www.aryanupadhyay.tech/post/bahdanau-vs-luong-attention-architecture-math-and-differences-explained696cf711322ac077fef85729Mon, 16 Feb 2026 04:19:28 GMTAryan<![CDATA[Introduction to Transformers: The Neural Network Architecture Revolutionizing AI]]>https://www.aryanupadhyay.tech/post/introduction-to-transformers-the-neural-network-architecture-revolutionizing-ai696ca3623e23fce293785ad6Sat, 14 Feb 2026 09:30:51 GMTAryan<![CDATA[Attention Mechanism Explained: Why Seq2Seq Models Need Dynamic Context]]>https://www.aryanupadhyay.tech/post/attention-mechanism-explained-why-seq2seq-models-need-dynamic-context696624e79c3c03a0a5e3341bThu, 12 Feb 2026 10:03:36 GMTAryan<![CDATA[Encoder–Decoder (Seq2Seq) Architecture Explained: Training, Backpropagation, and Prediction in NLP]]>https://www.aryanupadhyay.tech/post/encoder-decoder-seq2seq-architecture-explained-training-backpropagation-and-prediction-in-nlp695a0e4abd1cfb4bde7ae394Tue, 10 Feb 2026 07:32:05 GMTAryan<![CDATA[From RNNs to GPT: The Epic History and Evolution of Large Language Models (LLMs)]]>https://www.aryanupadhyay.tech/post/from-rnns-to-gpt-the-epic-history-and-evolution-of-large-language-models-llms6959fb67bd1cfb4bde7abb5cSun, 08 Feb 2026 07:19:27 GMTAryan<![CDATA[What is a GRU? Gated Recurrent Units Explained (Architecture & Math)]]>https://www.aryanupadhyay.tech/post/what-is-a-gru-gated-recurrent-unit6985edad2afb5c3741be2c6cFri, 06 Feb 2026 13:45:31 GMTAryan