Recorded Talks

Invited talks

Exploring Bit-Level Patterns for Efficient NN Quantization and Deployment

Robust DNN Inference under Input, Quantization and On-Chip Stochastic Noises

Stories of the Generation Z AI Researchers

Towards Efficient DNN Architecture

Conference talks

Global Vision Transformer Pruning with Hessian-Aware Saliency

CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification

Hero: Hessian-enhanced robust optimization for unifying and improving generalization and quantization performance

BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization

DVERGE: diversifying vulnerabilities for enhanced robust generation of ensembles

Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification

Deephoyer: Learning sparser neural network with differentiable scale-invariant sparsity measures

Exploring Bit-Slice Sparsity in Deep Neural Networks for Efficient ReRAM-Based Deployment