Bin Xiao

Adam Can Mitigate Class Imbalance Without Element-Wise Gradient Normalization

IOShift: Backdoor Defense via Model Bias Shift in Federated Learning

Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models

Understanding Input Transformation-Based Attacks via Target Function Space Expansion

Continual Knowledge Adaptation for Reinforcement Learning

Activating More Advantageous Neurons Can Improve Adversarial Transferability

Test-Time Learning for Large Language Models