{"@attributes":{"version":"2.0"},"channel":{"title":"Introduction on Oriol Al\u00e0s Cerc\u00f3s","link":"https:\/\/oriolac.github.io\/tags\/introduction\/","description":"Recent content in Introduction on Oriol Al\u00e0s Cerc\u00f3s","generator":"Hugo -- 0.150.0","language":"en-us","copyright":"Oriol Al\u00e0s Cerc\u00f3s","lastBuildDate":"Sat, 25 Oct 2025 12:31:23 +0100","item":[{"title":"From Words to Vectors: A Dive into Embedding Model Taxonomy","link":"https:\/\/oriolac.github.io\/posts\/20251025-embedding-models\/","pubDate":"Sat, 25 Oct 2025 12:31:23 +0100","guid":"https:\/\/oriolac.github.io\/posts\/20251025-embedding-models\/","description":"
Embedding models are foundational in modern NLP, turning raw text into numerical vectors that preserve semantic\nsignificance. These representations power everything from semantic search to Retrieval-Augmented Generation or Prompt\nEngineering for LLM Agents. With growing demand for domain-specific applications, understanding which is the best fit\nfor your system is more important than ever.<\/p>\n
Introduction<\/h1>\n
In modern NLP, a text embedding<\/em> is a vector that represents a piece of text in a mathematical space. The magic of\nembeddings is that they encode semantic meaning: texts with similar meaning end up with vectors that are close together.\nFor example, an embedding model might place “How to change a tier” near “Steps to fix a flat tire” in its vector space,\neven though the wording is different. This property makes embedding models incredibly useful for tasks like search,\nclustering or recommendation, where we care about semantic similarity<\/em> rather than exact keyword matches. By converting\ntext into vectors, embedding models allow computers to measure meaning and relevance via distances in vector space.<\/p>"},{"title":"The Generative Trilemma: A quick overview","link":"https:\/\/oriolac.github.io\/posts\/20250710-starting-diffusion\/","pubDate":"Thu, 10 Jul 2025 12:13:48 +0100","guid":"https:\/\/oriolac.github.io\/posts\/20250710-starting-diffusion\/","description":"
Generative models are a class of machine learning that learn a representation of the data trained on and they model the\ndata itself.<\/p>\n
Ideally, generative models should satisfy the following key requirements in a real environment:<\/p>\n
\n
High quality samples<\/strong> refers to those samples that captures the underlying patterns and\nstructures present in the data making them indistinguishable from human observers.<\/li>\n
Fast Sampling<\/strong> is about the efficiency of image generation and the computational overhead\nthat can cause generative models.<\/li>\n
Mode Coverage\/Diversity<\/strong> points out how the model is able to generate a full range of\nmods and diverse patterns present in the training data<\/li>\n<\/ul>\n
\n\n\n\nFig. 1. The Generative Learning Trilemma\n<\/figcaption>\n<\/figure>\n<\/p>"},{"title":"Introduction to Attention Mechanism and Transformers","link":"https:\/\/oriolac.github.io\/posts\/20241029-attention\/","pubDate":"Mon, 17 Feb 2025 12:31:23 +0100","guid":"https:\/\/oriolac.github.io\/posts\/20241029-attention\/","description":"
Transformers have demonstrated excellent capabilities and they overcome challenges such NLP<\/em>, Text-To-Image Generation<\/em> or Image Completion<\/em>\nwith large datasets, great model size and enough compute.\nTalking about transformers nowadays is as casual as talking about CNNs<\/em>, MLPs<\/em> or Linear Regressions<\/em>. Why not take a glance through this state-of-the-art architecture?<\/p>\n
In this post, we\u2019ll introduce the Sequence-to-Sequence (Seq2Seq) paradigm, explore the attention mechanism, and provide a detailed,\nstep-by-step explanation of the components that make up transformer architectures.<\/p>"}]}}
![\"alt](\"https:\/\/oriolac.github.io\/posts\/2025\/gen_tril\/gen_tril.png#center\" "\\"Fig.")
\n