Diffusion-based recommenders learn user preferences by denoising interaction histories, but the added noise can distort the original preference signals. Flow-based collaborative filtering (CF) instead learns a discrete path from a sampled source to the user's observed training interactions (the target history), enablin...
Cheng-Hao Wu, Yong-Qi Zhou, Jin Chen et al.· 0 citations
ChronicleRec is a pre-train-and-transfer framework that compresses an ultra-long behavior sequence once into a chronologically ordered set of Chronicle Tokens, which can be cached per user, decoupling ultra-long sequence modeling from online candidate scoring.
Chengkai Huang, Yu-Bin Sheng, Liang Guo et al.· 0 citations
DLMRec is proposed, a discrete diffusion language model tailored for recommendation that offers a compelling alternative to autoregressive generation and introduces three key components to bridge diffusion language modeling with recommendation.
Chengyi Liu, Yong-Qi Zhou, Jun-Wei Pan et al.· arXiv.org· 1 citation
DASH is a decision-aware user simulator that jointly generates thinking traces and predicts behavioral actions from heterogeneous cross-domain histories and tailors a rubric-based reward model that evaluates thinking traces along form, content, and logic for RL training.
