Tag
A tweet discusses the storage concerns of late interaction models and shares interesting results on hierarchical pooling and asymmetric quantization techniques.
Mixedbread Search introduces asymmetric quantization for late interaction retrieval, achieving near-lossless quality with 97% storage reduction by storing document vectors as binary signs while keeping query vectors at higher precision.
Mixedbread AI introduces asymmetric quantization for late interaction retrieval, achieving 32x storage reduction with minimal quality loss by storing document vectors as binary signs while keeping query vectors high-precision, making late interaction practical for billion-scale production systems.