Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter
Lei Jiang, Wen Ge, Niels Cariou-Kotlarek +6
Diffusion models have achieved state-of-the-art results in generative modelling but remain computationally intensive at inference time, often requiring thousands of discretization…
cs.LG2024
Neural Controlled Differential Equations with Quantum Hidden Evolutions
Lingyi Yang, Zhen Shao
We introduce a class of neural controlled differential equation inspired by quantum mechanics. Neural quantum controlled differential equations (NQDEs) model the dynamics by analog…
cs.LG2024
Q-learning as a monotone scheme
Lingyi Yang
Stability issues with reinforcement learning methods persist. To better understand some of these stability and convergence issues involving deep reinforcement learning methods, we…