2 papers
cs.LG2025
DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scaling
Qingyuan Wang, Barry Cardiff, Antoine Frappé +2
Conventional deep learning (DL) model compression and scaling methods focus on altering the model's components, impacting the results across all samples uniformly. However, since s…
cs.AI2025
Tiny Models are the Computational Saver for Large Models
Qingyuan Wang, Barry Cardiff, Antoine Frappé +2
This paper introduces TinySaver, an early-exit-like dynamic model compression approach which employs tiny models to substitute large models adaptively. Distinct from traditional co…