3 papers
cs.IR2026
Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design
Bojian Hou, Xiaolong Liu, Xiaoyi Liu +26
Deriving predictable scaling laws that govern the relationship between model performance and computational investment is crucial for designing and allocating resources in massive-s…
cs.IR2026
LLM Retrieval for Stable and Predictable Ad Recommendations
Vinodh Kumar Sunkara, Satheeshkumar Karuppusamy, Hangjun Xu +13
Traditional ads recommendation systems have primarily focused on optimizing for prediction accuracy of click or conversion events using canonical metrics such as recall or normaliz…
cs.IR2025
Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID
Carolina Zheng, Minhui Huang, Dmitrii Pedchenko +15
The exponential growth of online content has posed significant challenges to ID-based models in industrial recommendation systems, ranging from extremely high cardinality and dynam…