Author name: Seungmin Lee, Jeonghwan Lee, Hyunkuk Lim, Sejoon Kim, Mingi Sung

arXiv:2604.17257v2 Announce Type: replace-cross
Abstract: Recent text embedding models are often adapted to specialized domains via contrastive pre-finetuning (PFT) on a naive collection of scattered, heterogeneous tasks. However, this approach often …

arXiv:2604.17257v1 Announce Type: new
Abstract: Recent text embedding models are often adapted to specialized domains via contrastive pre-finetuning (PFT) on a naive collection of scattered, heterogeneous tasks. However, this approach often introduces…