collaborators

5 papers

cs.AI2026

MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging

Junxi Wang, Te Sun, Jiayi Zhu +9

Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory intro…

cs.AI2026

Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting

Siyuan Li, Yunjia Wu, Yiyong Xiao +5

Temporal knowledge graph (TKG) forecasting requires predicting future facts by jointly modeling structural dependencies within each snapshot and temporal evolution across snapshots…

cs.AI2025

Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models

Ruitong Liu, Boxu Lin, Peize Li +4

Fusing Knowledge Graphs with Large Language Models (LLMs) is crucial for knowledge-intensive tasks like knowledge graph completion. Existing LLM-based approaches typically inject g…

cs.AI2025

Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing

Siyuan Li, Yan Wen, Ruitong Liu +4

Semantic context surrounding a triplet is crucial for Knowledge Graph Completion (KGC), providing vital cues for prediction. However, traditional node-based message pas…

cs.CL2025

Flow-Modulated Scoring for Semantic-Aware Knowledge Graph Completion

Siyuan Li, Ruitong Liu, Yan Wen +4

Knowledge graph completion demands effective modeling of multifaceted semantic relationships between entities. Yet, prevailing methods, which rely on static scoring functions over…