Huanrui Yang

6

Papers

26

Total Citations

Papers (6)

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers

MSQ: Memory-Efficient Bit Sparsification Quantization

PAT: Pruning-Aware Tuning for Large Language Models

Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting