Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Hamming Attention Distillation: Binarizing Keys and Queries for Efficient Long-Context Transformers
Mark Horton, Tergel Molom-Ochir, Peter Liu +8
Pre-trained transformer models with extended context windows are notoriously expensive to run at scale, often limiting real-world deployment due to their high computational and mem…
cs.LG2024
Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency
Bhavna Gopal, Huanrui Yang, Jingyang Zhang +2
Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an inno…