분류 전체보기182 [Paper Review] Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization (ICLR 2026) A recent ICLR 2026 paper proposes a more direct approach to hybrid retrieval: instead of fusing outputs, GQR performs test-time optimization on the query embedding itself. This post breaks down the GQR architecture, the experimental results on the ViDoRe benchmark, and why this approach can be an efficient option for high-performance RAG pipelines.Guided Query Refinement (GQR) — ICLR 2026 — arXi.. 2026. 2. 18. Recent Multimodal RAG Papers (ColPali, SV-RAG, URaG, MetaEmbed) Multimodal Retrieval-Augmented Generation (RAG) has evolved rapidly over the last two years. Although these systems are often discussed under the same umbrella, they operate at different architectural levels, retrieval units, and deployment regimes.This post examines four influential systems:ColPali (ICLR 2025) — arXiv | codeSV-RAG (ICLR 2025) — arXiv | codeURaG (AAAI 2026) — arXiv | codeMetaEmb.. 2026. 2. 14. Paper Review: Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning In this post, I’m reviewing Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning (ACL 2025 ) without exotic training tricks. The recipe — called LLM-SRT — keeps a frozen Whisper encoder, adds a lightweight speech adapter (Q-Former + MLP), and fine-tunes in three stages: (1) ASR, (2) speech-aided MT (SMT/MMT), and (3) SRT, where the model generates both a transcript.. 2025. 10. 11. Understanding and Comparing Embedding Models for RAG and Vector Search In the rapidly evolving landscape of artificial intelligence, embedding models have emerged as the unsung heroes powering everything from semantic search to recommendation systems. These sophisticated models transform unstructured data into numerical vectors that preserve semantic meaning, enabling machines to understand and process human language with unprecedented accuracy. What Are Embedding .. 2025. 5. 26. Model Context Protocol (MCP): Shaping the Future of AI Agents The Model Context Protocol (MCP) is an innovative protocol designed to enhance AI model interactions through advanced context management. This blog post explores what MCP is, how it works, and how developers can leverage its capabilities using the Python client example. What is the Model Context Protocol (MCP)?The Model Context Protocol (MCP) is a sophisticated protocol that enables more effecti.. 2025. 5. 17. Understanding FastAPI: Building Production-Grade Asynchronous Applications with MCP As the demand for real-time, responsive, and scalable AI applications grows, building robust asynchronous APIs becomes essential. In this guide, we explore FastAPI, a high-performance web framework for Python, and how it can power production-grade asynchronous applications—particularly those integrating with AI orchestration protocols like the Model Context Protocol (MCP). The code below is base.. 2025. 5. 17. Building a Financial RAG Chatbot Using LLaMA, Streamlit and RunPod (VSCode) In this tutorial, we’ll walk through the process of building a Financial Question-Answering chatbot using Retrieval-Augmented Generation (RAG), LLaMA 3, and Streamlit. We’ll deploy our solution on RunPod’s GPU cloud environment for cost-effective development and testing.What We’re BuildingWe’ll create an investment education chatbot that:Retrieves relevant information from financial educational .. 2025. 5. 16. TensorFlow vs PyTorch vs Keras: A Beginner-Friendly Comparison of Deep Learning Frameworks Whether you’re just stepping into the world of deep learning or already exploring complex neural networks, choosing the right framework is crucial. Among the many, three stand out: TensorFlow, PyTorch, and Keras. These tools power research breakthroughs, industrial AI products, and educational curriculums alike.In this guide, we’ll explore:What each framework is and who it’s forTheir strengths a.. 2025. 5. 14. 2018 아모레퍼시픽 마케팅 공모전 수상작 (우수상) 2018년 자료지만, 마케팅 덕후였던 대학 시절 처음으로 참여한 마케팅 공모전에서 STRATEGY 부문 우수상(2위)을 받았던 출품작을 추억삼아 올려봅니다 🩵 이때 당시 수상 특전으로 아모레퍼시픽에서 마케팅 인턴십 기회도 얻을 수 있었습니다! 슬쩍 듣기로는 900팀 정도 참여했다고 들었는데, 정말 운이 좋았던 것 같습니다 :) 2024. 5. 29. 2021년 업데이트 (feat. 이직) 너무 오랜기간 블로그를 쉬고 업데이트를 하게 되네요. 정말 운 좋게 카카오 계열사에 기획 직무로 이직을 하게 되었습니다. 원하던 데이터 관련 직무는 아니지만 가고 싶던 기업인데 이렇게 큰 행운이 찾아올 것이라고 생각도 못했었죠. 저만 긴장했던 수습 기간이 지나고, 운동도 하고 살도 빼고 하니 벌써 2월이네요. 올해 초 목표였던 석사 졸업은 올해 8월로 미뤘습니다. 훌륭한 분들 사이에 있으니 욕심이 커지는 것은 어쩔 수 없더라구요. 목표가 커진 만큼 성장하겠죠? 그리고 영어 블로그를 시작해볼까 해서 2개를 팠습니다. 여기서는 좀더 연구자/개발자 적인 글을 남겨볼까 하는데 아직 프스트는 없습니다. 언젠가 영어를 자유롭게 쓰는 그날을 기대하며 매주 1회 이상을 써보려고 해요. Medium: https://m.. 2022. 2. 17. 이전 1 2 3 4 ··· 19 다음
