En Wang

A Unified Collaborative Representation Learning for Neural-Network Based Recommender Systems

2021 · IEEE Transactions on Knowledge and Data Engineering

With the boosting of neural networks, recommendation methods become significantly improved by their powerful ability of prediction and inference. Existing neural-network based recommender systems (NN-RSs) usually first employ matrix embedding (ME) as a pre-process to …

Indirect Online Preference Optimization via Reinforcement Learning

2025

Human preference alignment (HPA) aims to ensure Large Language Models (LLMs) responding appropriately to meet human moral and ethical requirements. Existing methods, such as RLHF and DPO, rely heavily on high-quality human annotation, which restrict …