<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:news="http://www.google.com/schemas/sitemap-news/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:image="http://www.google.com/schemas/sitemap-image/1.1" xmlns:video="http://www.google.com/schemas/sitemap-video/1.1"><url><loc>https://joanfihu.com/</loc></url><url><loc>https://joanfihu.com/about/</loc></url><url><loc>https://joanfihu.com/can-llms-find-knowledge-gaps-in-the-internet/</loc></url><url><loc>https://joanfihu.com/colpali-a-breakthrough-in-efficient-document-retrieval/</loc></url><url><loc>https://joanfihu.com/constraining-the-ai-agent-action-space-increases-reliability/</loc></url><url><loc>https://joanfihu.com/data-quality-over-capacity-internalizing-documents-into-lora-adapters-for-closed-book-qa/</loc></url><url><loc>https://joanfihu.com/document-chunking-for-rag-retrieval-augmented-generation/</loc></url><url><loc>https://joanfihu.com/evaluating-adepts-fuyu-model-for-ui-navigation/</loc></url><url><loc>https://joanfihu.com/evolution-of-media-from-ancient-communications-to-ai-generated-content/</loc></url><url><loc>https://joanfihu.com/introduction-to-building-llm-applications/</loc></url><url><loc>https://joanfihu.com/kaggle-docs-qa-with-gemma-data-collection-dataset-generation-fine-tuning-rag-colbert-re-ranker-evaluation/</loc></url><url><loc>https://joanfihu.com/memgpt-enhancing-llm-capabilities-through-operating-system-principles/</loc></url><url><loc>https://joanfihu.com/simplifying-language-image-pre-training-with-sigmoid-loss/</loc></url><url><loc>https://joanfihu.com/software-engineering-has-expanded-choosing-between-rules-prompts-chains-and-agents/</loc></url><url><loc>https://joanfihu.com/the-generative-internet/</loc></url><url><loc>https://joanfihu.com/the-platform-for-the-universal-personal-assistant/</loc></url><url><loc>https://joanfihu.com/vqa-and-image-chunking-for-gpt-4v-and-gemini/</loc></url></urlset>