↓Skip to main content

🏢 Karlsruhe Institute of Technology

Variational Distillation of Diffusion Policies into Mixture of Experts
·3451 words·17 mins· loading · loading
AI Generated AI Applications Robotics 🏢 Karlsruhe Institute of Technology
VDD distills complex diffusion policies into efficient Mixture of Experts (MoE) models via variational inference, enabling faster inference and improved performance in behavior learning.
The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
·215 words·2 mins· loading · loading
AI Theory Optimization 🏢 Karlsruhe Institute of Technology
Researchers found the minimax optimal rate of HSIC estimation for translation-invariant kernels is O(n⁻¹/²), settling a two-decade-old open question and validating many existing HSIC estimators.
Provably Safe Neural Network Controllers via Differential Dynamic Logic
·2824 words·14 mins· loading · loading
AI Theory Safety 🏢 Karlsruhe Institute of Technology
Verifiably safe AI controllers are created via a novel framework, VerSAILLE, which uses differential dynamic logic and open-loop NN verification to prove safety for unbounded time horizons.
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
·3296 words·16 mins· loading · loading
Machine Learning Meta Learning 🏢 Karlsruhe Institute of Technology
EBiL-HaDS, a novel adaptive domain scheduler, significantly boosts open-set domain generalization by strategically sequencing training domains based on model reliability assessments.