Yifan Zhu

Associate Professor@Beijing University of Post and Telecommunications·中国·OpenReview

研究方向

parameter-efficient finetuning · mixture of experts · large language model · graph neural networks · datamining in neuroscience · recommendation systems · knowledge graph · educational data mining · social media analysis

Yifan Zhu

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding

Toward Robust Image Manipulation Localization: A Novel Framework with VLMs and Weight-Aware Decoder

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

A Novel Query-Driven Multi-Stage Alternating Feature Extraction and Interaction Network for Image Manipulation Localization

C-Flat Turbo: A Faster Path to Continual Learning

GenFlow: Constrained Long-Form Text Generation via Adaptive Workflow Optimization

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation

INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph

Complex Numerical Computation with Numerical Semantic Pre-training Framework

InteractiveCOT: Aligning Dynamic Chain-of-Thought Planning for Embodied Decision-Making