A box of core libraries for recommendation model development
Fast and Flexible Neural Click Models in JAX
ICTIR 2025 - Unidentified and Confounded? Understanding Two-Tower Models for Unbiased Learning to Rank
Deploying a Multimodal Recommender System on Kubernetes featuring Cold Start handling, Bloom Filters, and Feature Caching.
Two-stage recommender system: PyTorch Two-Tower retrieval + FAISS ANN candidate generation + XGBoost LambdaMART re-ranking, served via FastAPI with a Streamlit demo and MLflow experiment tracking.
This repo is made for Football analytics and is based on FIFA 24 data
Two Tower Recommender System for Teamu
Unofficial implementation of model from Embedding-based Product Retrieval in Taobao Search
End-to-end Two-Stage Recommendation Architecture (Two-Tower Retrieval + CatBoost Ranking) for H&M Personalized Fashion. Engineered as a Python package..
A production-grade two-stage recommender system built on MovieLens 25M featuring PyTorch Two-Tower candidate generation, FAISS sub-millisecond vector retrieval (<1ms), an XGBoost second-stage ranker, cold-start fallback pathways, and a dark glassmorphism Streamlit dashboard.
Hybrid recommender system combining two-tower retrieval, FAISS and learning-to-rank.
Candidate Generation with Two-Tower Model for Recommendation System trained on MIND (Microsoft News Dataset).
A rigorous, code-first curriculum for learning Recommender Systems — from collaborative filtering and latent factors to deep learning, retrieval, ranking, and responsible recommendation.
A complete e-commerce search system with retrieval, pre-ranking, and re-ranking stages using fine-tuned deep learning models. Built on Amazon Shopping Queries Dataset with ESCI relevance framework for modern product search.
To associate your repository with the two-tower-models topic, visit your repo's landing page and select "manage topics."