activity
20202026
most citedCompounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network

36 citations · 36 across the 4 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.IR2026

The Pre-Training Study of Expanded-SPLADE Models on Web Document Titles

Hiun Kim, Tae Kwan Lee, Taeryun Won

Masked Language Modeling (MLM) pre-training is one of the primary ways to initialize Neural Information Retrieval (IR) models prior to retrieval fine-tuning. However, studies show…