Geyong Min

Robustify Spiking Neural Networks via Dominant Singular Deflation under Heterogeneous Training Vulnerability

Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation

Breaking Gradient Temporal Collinearity for Robust Spiking Neural Networks

Blockwise Hadamard high-Rank Adaptation for Parameter-Efficient LLM Fine-Tuning

CoM-V2I: Communication-Efficient Multimodal Cooperative Perception via Codebook Pruning and Multiscale Fusion

Efficient Spectral Graph Diffusion based on Symmetric Normalized Laplacian

CLAD: Continual Learning for Robust Adversarial Text Detection and Repair in Resource-Constrained Scenarios

Diffusion-Advection Transformer for Air Quality Prediction

Spatio-Temporal Dependency-Aware Neuron Optimization for Spiking Neural Networks

How Does Cross-Layer Correlation in Deep Neural Networks Influence Generalization and Adversarial Robustness?