Yisen Wang

Latest

• Optimization-induced Implicit Graph Diffusion
• Training Much Deeper Spiking Neural Networks with a Small Number of Time-Steps
• Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
• Reparameterized Sampling for Generative Adversarial Networks
• Demystifying Adversarial Training via A Unified Probabilistic Framework
• Dissecting the Diffusion Process in Linear Graph Convolutional Networks
• Efficient Equivariant Network
• Gauge Equivariant Transformer
• Residual Relaxation for Multi-view Representation Learning
• Improving Adversarial Robustness via Channel-wise Activation Suppressing
• Towards A Unified Understanding and Improving of Adversarial Transferability
• Unlearnable Examples: Making Personal Data Unexploitable
• Adversarial Weight Perturbation Helps Robust Generalization
• Normalized Loss Functions for Deep Learning with Noisy Labels
• Improving Adversarial Robustness Requires Revisiting Misclassified Examples
• Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
• Symmetric Cross Entropy for Robust Learning with Noisy Labels
• On the Convergence and Robustness of Adversarial Training