Jundong Li

Associate Professor@University of Virginia·美国·OpenReview

研究方向

Machine Learning Safety · Large Language Model · Algorithmic Fairness · Causal Inference · Trustworthy AI · Graph Mining · Graph Machine Learning · Feature Selection

Jundong Li

Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping

Energy-Based Transformers are Scalable Learners and Thinkers

Probing to Refine: Reinforcement Distillation of LLM Reasoners via Explanatory Inversion

Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations

GCSGNN: Towards Global Counterfactual-Based Self-Explainable Graph Neural Networks

Adaptive Dual Prompting: Hierarchical Debiasing for Fairness-aware Graph Neural Networks

Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning

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

Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks

End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

Certified Defense on the Fairness of Graph Neural Networks

Knowledge Graph Retrieval-Augmented Generation via GNN-Guided Prompting

GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

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

Causal Effect Estimation with Mixed Latent Confounders and Post-treatment Variables

Edge Prompt Tuning for Graph Neural Networks

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models

Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems

Instance-Aware Graph Prompt Learning

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Fairness-Aware Graph Learning: A Benchmark

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

Channel-Wise Mixed-Precision Quantization for Large Language Models

GraphRCG: Self-Conditioned Graph Generation

Question-Aware Knowledge Graph Prompting for Large Language Models