EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation
Read the original on arXiv Machine Learning →EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation proposes a method that adds explicit item-level competition into the denoising process of Semantic ID (SID) generative recommendation. The approach builds a personalized posterior over feasible candidate items based on the current generation context and the user's recent interactions, then projects this distribution back to unresolved SID positions to guide subsequent token decisions. Experiments on four Amazon benchmarks show consistent improvements over strong baselines, with diagnostic analyses indicating that the gains stem from personalized transition evidence that preserves promising item hypotheses during denoising.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.