Jiliang Tang

A look at how LLMs improve user recommendations in various platforms.

Graph-JEPA offers a new method for analyzing complex graph data effectively.

An overview of copyright issues in generative AI and its impact.

An overview of skill learning and recognition in large language models.

Data poisoning threatens the integrity of in-context learning systems, revealing hidden vulnerabilities.

This research explores the potential of versatile graph foundation models.

This research examines how model and data size impact graph model performance.

New methods improve graph learning through non-discrete bandwidth masking techniques.

A new method enhances recommendations by combining user IDs and text insights.

A new approach improves link prediction accuracy using a mixture of expert models.

This paper analyzes the advantages of multi-head attention over single-head attention in machine learning tasks.

New methods improve the speed and accuracy of recommendation systems.

Examining issues of memorization in AI-generated images and its implications.

Exploring the impact of language models on student learning and teaching.

Researchers develop a model to improve graph learning using data from various sources.

Exploring the self-correction processes in language models and their effects.

This research enhances GNNs by adapting filters for different node patterns.

This article examines challenges in link prediction due to data distribution shifts.

This study highlights the need for improved inductive KGC datasets.

A new method to safeguard datasets against unauthorized usage in generative models.

A new dataset aims to improve the safety of text-to-image models against harmful content.

A new method reduces privacy risks in retrieval-augmented generation applications.

A new approach to efficiently solve large-scale linear programming problems.

New methods boost graph node classification accuracy with limited labeled data.

This article investigates LLM performance on graph-related reasoning tasks.

Discover how LLKD improves learning efficiency using smaller models.

This article discusses effective knowledge checking methods in RAG systems.

Learn how PDQP-Net speeds up solving Convex Quadratic Programs.

A new method simplifies graph analysis using specialized expert models.