Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Pooling-Aware Training Cuts Multi-Vector Retrieval Storage

AI summary

Tom Aarsen’s Hugging Face technical report introduces pooling-aware training for multi-vector embedding models, teaching encoders to retain useful information when similar token vectors are merged. The author reports that a factor-4 configuration reduced document vectors fourfold while retaining 97.8% of unpooled NanoBEIR nDCG@10, versus 94.6% for ordinary training, and provides reproducible Sentence Transformers code and checkpoints.

In-depth insight

Pooling-aware training could make multi-vector retrieval more storage-efficient while preserving more retrieval quality than ordinary training at the same vector budget.

Back to Articles

Token Pooling-Aware Training for Multi-Vector Embedding Models

Published November 11, 2026

Update on GitHub

Upvote 33

Tom Aarsen tomaarsen

#Sentence Transformers#ModernBERT#ColBERT#NanoBEIR#Fast-PLAID

Original · 12 min readRead the original
Group chat

No comments yet. Start the conversation.