Xiyuan Wang

Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning

Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs

Expressive Graph Neural Networks via Equivariant Use of Noise

GET: Rethinking Dynamic Graph Learning as Global Event Sequence Generation

GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

LIFT: Enhancing Long-Context Reasoning in Large Language Models via Long Input Fine-Tuning

GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization

Geometric Representation Condition Improves Equivariant Molecule Generation

On the Completeness of Invariant Geometric Deep Learning Models

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

Griffin: Towards a Graph-Centric Relational Database Foundation Model

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

Geometric Representation Condition Improves Equivariant Molecule Generation

GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model

Efficient Neural Common Neighbor for Temporal Graph Link Prediction