Tingwen Liu
3 papers · Latest:
Information Retrieval
Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users
NF-NPCDR improves cross-domain recommendation for cold-start users by modeling personalized multi-interest and common preferences with a novel neural process.
2604.25732
Natural Language ProcessingBeyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling
X-GRAM is a new framework that enhances embedding parameter efficiency and scaling in large language models by addressing memory growth and redundancy.
2604.21724
Natural Language ProcessingUnlocking the Power of Large Language Models for Multi-table Entity Matching
LLM4MEM uses LLMs to improve multi-table entity matching by resolving semantic inconsistencies, boosting efficiency, and pruning noisy entities.
2604.21238
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.