生成式推荐系统如何在大规模场景下重新定义 RecSys
How Generative Recommenders Are Redefining RecSys at Scale
NVIDIA 指出，LLM 的兴起正推动推荐系统从传统基于嵌入向量相似度的目标转向生成式目标，即根据用户历史序列预测大目录中的下一个动作或物品。推荐系统是消费互联网中最普遍的机器学习问题之一，但大规模训练与部署一直极为困难。
Recommender systems (RecSys) are one of the most ubiquitous machine learning problems in the consumer internet industry yet notoriously difficult to train and...
Recommender systems (RecSys) are one of the most ubiquitous machine learning problems in the consumer internet industry yet notoriously difficult to train and serve at scale. The advent of LLMs has inspired a shift from the traditional embedding-similarity-based objective to a generative one, where the goal is to predict the next action or item in a large catalog given a sequence of user histories.
来源：NVIDIA Developer Blog · developer.nvidia.com