3 papers
cs.IR2025
ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval
Fengran Mo, Jinghan Zhang, Yuchen Hui +4
Conversational search aims to satisfy users' complex information needs via multiple-turn interactions. The key challenge lies in revealing real users' search intent from the contex…
cs.LG2025
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
Samin Yeasar Arnob, Zhan Su, Minseon Kim +6
Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstrea…
cs.LG2024
Mixture of Latent Experts Using Tensor Products
Zhan Su, Fengran Mo, Prayag Tiwari +3
In multi-task learning, the conventional approach involves training a model on multiple tasks simultaneously. However, the training signals from different tasks can interfere with…