Omai

university

AI & ML interests

Search

Recent Activity

thongnt updated a collection about 2 months ago

MILCO Encoded Dataset

thongnt updated a dataset about 2 months ago

omai-research/milco-650m-nq-encoded

thongnt published a dataset about 2 months ago

omai-research/milco-650m-nq-encoded

View all activity

updated a collection about 2 months ago

MILCO Encoded Dataset

3 items • Updated May 15

updated a dataset about 2 months ago

omai-research/milco-650m-nq-encoded

Updated May 15 • 8

published a dataset about 2 months ago

omai-research/milco-650m-nq-encoded

Updated May 15 • 8

updated 2 collections about 2 months ago

MILCO: Multilingual Learned Sparse Retrieval

MILCO maps queries and documents from different languages into a shared English lexical space via a multilingual connector. • 4 items • Updated May 15 • 4

MILCO Encoded Dataset

3 items • Updated May 15

updated a dataset about 2 months ago

omai-research/milco-650m-browsecomp-encoded

Updated May 15 • 51

published a dataset about 2 months ago

omai-research/milco-650m-browsecomp-encoded

Updated May 15 • 51

updated a dataset about 2 months ago

omai-research/milco-650m-msmarco-encoded

Updated May 15 • 8

published a dataset about 2 months ago

omai-research/milco-650m-msmarco-encoded

Updated May 15 • 8

updated a dataset 2 months ago

omai-research/bge-multilingual-distillation-dataset

Viewer • Updated May 3 • 1.39M • 670

published a dataset 2 months ago

omai-research/bge-multilingual-distillation-dataset

Viewer • Updated May 3 • 1.39M • 670

updated a dataset 3 months ago

omai-research/finetranslation-edu

Viewer • Updated Apr 21 • 380M • 452

published a dataset 3 months ago

omai-research/finetranslation-edu

Viewer • Updated Apr 21 • 380M • 452

updated 2 models 3 months ago

omai-research/milco-650m

Feature Extraction • Updated Apr 16 • 739 • 6

omai-research/milco-300m

Feature Extraction • Updated Apr 11 • 21 • 3

authored a paper 3 months ago

Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector

Paper • 2510.00671 • Published Oct 1, 2025 • 3

updated a collection 3 months ago

MILCO: Multilingual Learned Sparse Retrieval

MILCO maps queries and documents from different languages into a shared English lexical space via a multilingual connector. • 4 items • Updated May 15 • 4

authored 2 papers 3 months ago

A Unified Framework for Learned Sparse Retrieval

Paper • 2303.13416 • Published Mar 23, 2023 • 1

Sparton: Fast and Memory-Efficient Triton Kernel for Learned Sparse Retrieval

Paper • 2603.25011 • Published Mar 26 • 1