Industrial recommendation ranking models typically scale along two modeling axes: feature interaction over heterogeneous user, item, context, and cross features, and sequence modeling over long, informative, and multi-type user behavior histories. We find that scaling either capability in isolation is insufficient, as...
Yun-Tao Zheng, Miao Zhang, Ya-Dong Ding et al.· 0 citations
OneTrans-V2 is presented, one Transformer that unifies the entire cascade of retrieval, pre-rank, and fine-rank and introduces Decision-Conditioned Generative Retrieval (DCGR), which predicts a decision prefix describing the upcoming interaction and generates items conditioned on it, allowing business objectives to ste...
Han-Nan Cao, Jun Guo, Hao-Lei Pei et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.