Jun Yang
Nvidia (United States) · 15 works · 316 citations · h-index 8
Top works
- Dynamic clustering of evolving streams with a single pass
- Ansor: Generating High-Performance Tensor Programs for Deep Learning
- Auto-Ensemble: An Adaptive Learning Rate Scheduling Based Deep Learning Model Ensembling
- DAPPLE: A Pipelined Data Parallel Approach for Training Large Models
- Efficient Pipeline Planning for Expedited Distributed DNN Training
- ModelShield: A Generic and Portable Framework Extension for Defending Bit-Flip based Adversarial Weight Attacks
- Extremely Low Footprint End-to-End ASR System for Smart Device
- Detecting TensorFlow Program Bugs in Real-World Industrial Environment
- Optimizing DNN Compilation for Distributed Training With Joint OP and Tensor Fusion
- DISC: A Dynamic Shape Compiler for Machine Learning Workloads
- Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads
- 1×N Block Pattern for Network Sparsity.
- 1$\times$N Block Pattern for Network Sparsity
- Extremely Low Footprint End-to-End ASR System for Smart Device
- An Application-Oriented Autoscaler Based on Deep Learning