Évaluation de la pertinence (question ↔ article juridique) en français. Pipeline complet (prépa → modèles → soumission) avec CamemBERT en bi-encodeur calibré (MSE/Spearman), + variantes cross-encoder.

한국어/영어 발음 유사도 기반 매핑 시스템. ASR 결과를 데이터베이스 용어와 정확히 매칭해주는 오픈소스 도구입니다.한국어-영어 간 발음 변환, Levenshtein 거리 기반 매칭, 사용자 정의 매핑을 지원하여 음성 인터페이스 정확도를 높입니다

code for paper https://arxiv.org/pdf/2510.00324 to be presented at sigir-ap 2025

A Virtual Reality based Driver perspective safety simulation for pedestrian safety project using Unity 3D and Meta Quest 3 to activate and challenge AEB in ADAS virtually for efficient automotive testing based on Euro NCAP standards.

This is the code repository for the blog post "Can we assess span-level relevance with dense embedding models?".

AI-powered semantic search engine for products. FastAPI + MySQL + sentence-transformers.

Simple PHP search engine that supports Russian and English morphology

📤 Git Auto Commit keeps your GitHub repository active by automatically creating new commits. It boosts visibility and engagement while keeping your commit history clean and clutter-free.

Jupyter notebooks to help with search relevancy measurements, optimized for Quepid.

A repository for the UBC MDS Capstone team to develop a metadata extractor for Neotoma

Model that converts e-commerce product descriptions into natural user search queries.

Search Request Processor: pipeline for transformation of queries and results inline with a search request.

NoMIRACL: A multilingual hallucination evaluation dataset to evaluate LLM robustness in RAG against first-stage retrieval errors on 18 languages.

Giga Parsers 🦾😎

This repository showcases an AI tool designed to evaluate the average selling price of new constructions in Miami, FL. It offers a detailed breakdown of price ranges and includes features to assess prices by specific ZIP codes, providing valuable insights into the primary real estate market in Miami.

This repository evaluates the average selling price of properties in Wroclaw (Poland), offering a detailed breakdown of price ranges. It includes tools to assess prices at specific addresses, providing insights into the primary real estate market. This aids in informed decision-making for buyers, sellers, and investors.

This repository evaluates the average selling price of properties in Lodz, Poland, offering a detailed breakdown of price ranges. It includes tools to assess prices at specific addresses, providing insights into the primary real estate market. This aids in informed decision-making for buyers, sellers, and investors.

This repository evaluates the average selling price of properties in Warsaw, offering a detailed breakdown of price ranges. It includes tools to assess prices at specific addresses, providing insights into the primary real estate market. This aids in informed decision-making for buyers, sellers, and investors.

TasteRank: Personalized Image Search and Recommendation. This research project proposes an AI-based method for scoring photos on relevance to user interests. TasteRank leverages language and vision models, including Mistral LLMs and OpenAI’s CLIP, and applies multimodal machine-learning techniques.

Elasticsearch/Solr Sandbox for exploring explain information and tweaking