most citedEntropy-based Guidance of Deep Neural Networks for Accelerated Convergence and Improved Performance

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts

Sebastián Andrés Cajas Ordóñez, Luis Fernando Torres Torres, Mackenzie J. Meni +6

Deploying deep neural networks on resource-constrained devices faces two critical challenges: maintaining accuracy under aggressive quantization while ensuring predictable inferenc…