efficient-nlp

Tag

Cards List
#efficient-nlp

KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking

Hugging Face Daily Papers · 3d ago Cached

KaLM-Reranker-V1 is a fast reranker that decouples query and passage computation using an encoder-decoder architecture with Matryoshka embedding pooling and cross-attention, achieving state-of-the-art reranking performance on BEIR and competitive results on multilingual benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback