Late Interaction Models
Late Interaction Models is a class of neural information retrieval models that belong to the broader category of passage retrieval methods, distinguished by delayed computation of fine-grained interactions between query and document tokens until late in the encoding process, thereby balancing efficiency and contextual fidelity in relevance ranking.
14
Publications
2.2K
Citations
57
Authors
16
Institutions
Publications per year
2017–2026
11
14
Omar Khattab, Matei Zaharia · 2020 · 1.1K citations
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
Keshav Santhanam, Omar Khattab, Jon Saad-Falcon et al. · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · 2022 · 277 citations · Full text
FILIP: Fine-grained Interactive Language-Image Pre-Training
Lewei Yao, Runhui Huang, Lu Hou et al. · arXiv (Cornell University) · 2021 · 206 citations · Full text
1–5 of 14
57
4
h-index
3
h-index
3
h-index
3
h-index
2
h-index
1–5 of 57
16
Stanford University
Stanford, United States
4 h-index
10 publications
3.9K citations

University of Crete
Rethymno, Greece
1 h-index
1 publications
116 citations

University of Glasgow
Glasgow, United Kingdom
1 h-index
1 publications
12 citations
University of Washington
Seattle, United States
1 h-index
3 publications
105 citations

Finnish Meteorological Institute
Helsinki, Finland
1 h-index
2 publications
44 citations
University of Michigan
Ann Arbor, United States
1 h-index
2 publications
44 citations

University of Waterloo
Waterloo, Canada
1 h-index
4 publications
140 citations
Georgia Institute of Technology
Atlanta, United States
1 h-index
5 publications
1.4K citations
1–8 of 16
Repository · 4 publications · 473 citations
4
h-index
Conference · 1 publications · 277 citations
1
h-index
1 publications · 31 citations
1
h-index
Conference · 1 publications · 14 citations
1
h-index
1 publications · 116 citations
1
h-index
1–5