EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens
Open Access
- 3 August 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3483-3494
Abstract
No abstract availableAll Related Versions
Funding Information
- The National Research Foundation, Singapore under its National Large Language Models Funding Initiative (AISG-NMLP-2024-002)
This publication has 16 references indexed in Scilit:
- Large language models make sample-efficient recommender systemsFrontiers of Computer Science, 2024
- Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation2024
- Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System2024
- A survey on large language models for recommendationWorld Wide Web, 2024
- Data-efficient Fine-tuning for LLM-based Recommendation2024
- Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation2024
- GPT understands, tooAI Open, 2024
- Prompt Distillation for Efficient LLM-based Recommendation2023
- LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems2023
- Lighter and Better: Low-Rank Decomposed Self-Attention Networks for Next-Item Recommendation2021