2 papers
cs.IR2026
Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction
Sejoon Oh, Fernando Amat Gil, Evan Smothers +11
Large-scale personalization is shifting from embedding-table retrieval to LLM-based recommenders that generate the Semantic ID (SID) of the item to recommend, where each SID is a s…
cs.CL2025
Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
Bangsheng Tang, Carl Chengyan Fu, Fei Kou +35
Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering c…