Xiao-Ming Wu

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models

SimGFM: Simplifying Discrete Flow Matching for Graph Generation

REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering

MSEarth: A Multimodal Scientific Dataset and Benchmark for Phenomena Uncovering in Earth Science

Assessing Large Language Models (LLMs) as Foundational Recommenders: A Multi-Domain, Multi-Dataset Benchmark

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

Beyond Random Masking: When Dropout meets Graph Convolutional Networks

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

Understanding Layer Significance in LLM Alignment

Understanding Layer Significance in LLM Alignment

Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence