Hyperbolic Embeddings in Qdrant
Why hierarchical data suits a curved space, and what that buys you.
Matin Mahmood and John Kupchanko
September 8, 2026
Embedding Research
Explore the research behind modern embeddings and neural retrieval. Dive into sparse neural models, late interaction, metric learning, and new baselines for hybrid search.
miniCOIL: on the Road to Usable Sparse Neural Retrieval
Our attempt to learn from drawbacks of modern sparse neural retrievers
Evgeniya Sukhodolskaya
May 13, 2025
Modern Sparse Neural Retrieval: From DeepCT to SPLADE++
How sparse neural retrievers evolved from DeepCT to SPLADE++, and when to choose them over BM25.
Evgeniya Sukhodolskaya
October 23, 2024
Late Interaction Retrieval with Dense Token Embeddings
Standard dense embedding models perform surprisingly well in late interaction scenarios.
Kacper Łukawski
August 14, 2024
BM42: Attention-Based Sparse Embeddings for Hybrid Search
An experimental attention-based sparse embedding approach for lexical search.
Andrey Vasnetsov
July 1, 2024
Layer Recycling and Fine-tuning Efficiency
Tradeoff between speed and performance in layer recycling
Yusuf Sarıgöz
August 23, 2022
Fine Tuning Similar Cars Search
How to use similarity learning to search for similar cars
Yusuf Sarıgöz
June 28, 2022
Metric Learning for Anomaly Detection
How to use metric learning to detect anomalies: quality assessment of coffee beans with just 200 labelled samples
Yusuf Sarıgöz
May 4, 2022
Advanced Introduction to Triplet Loss
What are the advantages of Triplet Loss and how to efficiently implement it?
Yusuf Sarıgöz
March 24, 2022
Metric Learning Tips & Tricks
How to train an object matching model and serve it in production.
Andrei Vasnetsov
May 15, 2021