PinnedPablo Hernandez Leal·Jul 18, 2024Interpretability of ColPali in Financial DocumentsRetrieval Augmented Generation (RAG) is one of the most common use cases of LLMs. The first step of Retrieval is usually performed with…A response icon1A response icon1
PinnedPablo Hernandez Leal·Jun 21, 2024Building a Financial Education Chatbot with Retrieval Augmented Generation (RAG)Part 2: RAG with embeddings and vector database
PinnedPablo Hernandez Leal·Sep 11, 2024Surya and EasyOCR: Vision Models and Data Extraction in Financial DocumentsSurya and EasyOCR
PinnedPablo Hernandez Leal·Jun 26, 2024From NeurIPS to the Real World: Key Takeaways from Competing in Pommerman“In theory there is no difference between theory and practice. In practice there is.” — Yogi Berra
Pablo Hernandez Leal·Nov 4, 2025DeepSeek-OCR: Vision Compression and Text Extraction in Financial Reports1. From Retrieval to ExtractionA response icon1A response icon1
Pablo Hernandez Leal·Mar 21, 2025How I use LLMs for codingLLMs have become an integral part of my coding. Not so long ago I’ve only used them for simple tasks (like boilerplate code), but recently…
Pablo Hernandez Leal·Mar 18, 2025Extracting Token-Level “Importance” From Cross-Encoders For Quick & Simple HighlightingAttention as explanation
Pablo Hernandez Leal·Feb 20, 2025Edge Cases in Financial Document ExtractionFinancial documents — ranging from invoices and statements to regulatory filings — are a staple of business operations. But extracting key…
Pablo Hernandez Leal·Feb 4, 2025Why Your OCR Results Differ: The Hidden Role of Embedded Fonts in PDFsSolving differences when using Poppler
Pablo Hernandez Leal·Jul 4, 2024Dynamic Pricing and Optimal Execution: Applied Reinforcement LearningTL;DR