Similar Items: Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation
- Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation
- One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation
- One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving
- Factorized Latent Reasoning for LLM-based Recommendation
- Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation
- Rethinking Convolutional Networks for Attribute-Aware Sequential Recommendation