Yada Zhu

Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning

Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs

Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative

Seeing What’s Wrong: A Trajectory-Guided Approach to Caption Error Detection

MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains

Mixture-of-Experts for Knowledge Graph Retrieval-Augmented Generation

RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking

HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations

Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play