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.
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.
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."