Haixin Wang

Dynamic Multi-sample Mixup with Gradient Exploration for Open-set Graph Anomaly Detection

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation

Do LLMs Really Understand Code? A Semantic Benchmark with Automated Question Generation and Evaluation

FourierFlow: Frequency-aware Flow Matching for Generative Turbulence Modeling

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

Omni-Mol: Multitask Molecular Model for Any-to-any Modalities

FLDmamba: Integrating Fourier and Laplace Transform Decomposition with Mamba for Enhanced Time Series Prediction

Flow Field Reconstruction with Sensor Placement Policy Learning

CellDJBench: Benchmark Datasets for Data-Driven Biological Fluid Simulation

Joint Modeling of Spatial and Temporal Multiscales in Molecular Dynamics