Xiaowen Dong

Bures-Wasserstein Flow Matching for Graph Generation

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin

Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning

Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity

Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks

Bundle Neural Network for message diffusion on graphs

On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning

Separation Power of Equivariant Neural Networks

On Measuring Long-Range Interactions in Graph Neural Networks

Neural Spacetimes for DAG Representation Learning

On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective

Training-Free Message Passing for Learning on Hypergraphs

Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation

Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning