Wei Xiang

TopoOT: Topology-Aware Optimal Transport for Test-Time Anomaly Segmentation

Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters

FedDOR: Orthogonal Initialization and Dual Regularization for Prototype Integrity in Heterogeneous Federated Learning

RankFlow: Property-aware Transport for Protein Optimization

ParaShield: Parameter-Level Directional Defense for Federated Backdoor Robustness

FedEquilibria: Towards Fair and Robust Federated Learning under Domain Skew

Q1Fold: A Qubit-Efficient Hybrid Quantum-Classical Convolutional Neural Network for RNA secondary Structure Prediction

Re-calibrating Progress: A Physics-Aware Benchmark to Expose the Evaluation Gap in Scientific Machine Learning

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation

Beyond KL-Regularization: Achieving Unbiased Direct Alignment through Diffusion $f_{\chi^n}$-Preference Optimization