Skip to the content.

粗排双塔相关

13 Oct 2025

双塔模型如何解决多任务预估问题:Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering

facebook的双塔召回:负样本为王:评Facebook的向量化召回算法

粗排的几个发展方向,来自:https://zhuanlan.zhihu.com/p/681808861

腾讯的增强双塔:HIT Model: A Hierarchical Interaction-Enhanced Two-Tower Model for Pre-Ranking Systems

A Dual Augmented Two-tower Model for Online Large-scale Recommendation

Mixture of virtual-kernel experts for multi-objective user profile modeling

Poly-encoders: architectures and pre-training strategies for fast and accurate multi-sentence scoring

IntTower: the Next Generation of Two-Tower Model for Pre-Ranking System

LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation

Equip Pre-ranking with Target Attention by Residual Quantization

RankFlow: Joint Optimization of Multi-Stage Cascade Ranking Systems as Flows

Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems

双塔为什么要做l2 norm,以及为什么需要温度系数

双塔做召回的经验