Reproduce “Cross-Country Code-Mixing for Generative Recommendation” 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
Yuan Gao, Hao Deng, Haibo Xing, Yi Xu, Lingyu Mu, Jinxin Hu, Yu Zhang, Xiaoyi Zeng
CMRec addresses recommendation across countries where user and item IDs and behavior sequences are country-specific, even under one model. It creates screened cross-country substitutions using shared multimodal item tokens, side-information checks, and context-aware reweighting. Across six countries/locales in each of two datasets, it leads reported offline metrics; online, only six-country aggregates rise 1.77% in advertising revenue and 2.64% in orders.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.