Yong Liu

Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering

Query-Centric Graph Retrieval Augmented Generation

Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control

Benchmarking and Enhancing Rational Preference Utilization for Personalized Assistants: A Pragmatic View

Unify in Isolation: Unified Data Synthesis for Divergent Multi-Stage Systems

Memory Type Matters: Enhancing Long-Term Memory in Large Language Models with Hybrid Strategies

SGMem: Sentence Graph Memory for Long-Term Conversational Agents

P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models

ToolACE: Winning the Points of LLM Function Calling

Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger

CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control