Tag
Introduces SaMer, an object-aware token merging framework that compresses image-side tokens for vision-language retrieval while preserving object-level evidence, achieving significant storage reduction and improved retrieval performance.
The authors found that regularizing ColBERT models fixes the efficient ANN methods MUVERA and SMVE, which had broken on modern ColBERT models, simplifying multi-vector retrieval infrastructure in an unexpected way.
TopK introduces semantic_index, a single schema annotation that abstracts multi-vector retrieval complexity for production systems, achieving state-of-the-art performance with sub-second latency and high throughput.
The author shares their work on reducing the cost of multi-vector retrieval by using k-means as top-1 sparse coding. Omar Khattab adds that late-interaction sparse retrieval with neuron-level inverted indexing on unsupervised sparse autoencoders works well.
This paper presents a single-stage sparse coding method using unsupervised sparse autoencoders and natural inverted indexing to accelerate multi-vector retrieval, outperforming traditional k-means based approaches.
This paper proposes Single-stage Sparse Retrieval (SSR), which replaces K-means clustering with sparse autoencoders and inverted indexing, achieving 15x faster indexing and halved retrieval latency while improving accuracy on the BEIR benchmark.