Reproduce “From Generation to Consumption: Personalized List Value Estimation for Re-ranking” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kaike Zhang, Xiaobei Wang, Xiaoyu Yang, Shuchang Liu, Hailan Yang, Xiang Li, Fei Sun, Qi Cao
CAVE re-ranks candidate recommendation lists by estimating the value users are predicted to consume. It encodes prefixes to estimate their values and combines personalized exit probabilities with a Weibull-fitted stochastic exit profile. On KuaiE, CAVE-GRN reaches 77.85 ± 1.80% uAUC versus 71.01 ± 0.57% for SDN-GRN with the same encoder; this is offline evidence and does not establish exit causes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.