Chang Liu

6 papers Peking University

• E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
• FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization
• How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective
• Long-term Intracortical Neural activity and Kinematics (LINK): An intracortical neural dataset for chronic brain-machine interfaces, neuroscience, and machine learning
• Near-Optimal Sample Complexity for Online Constrained MDPs
• One Filters All: A Generalist Filter For State Estimation