Europe
Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations
We study the problem of online adaptive policy selection for nonlinear time-varying discrete-time dynamical systems.
Geometric Neural Diffusion Processes Emile Mathieu University Of Cambridge Vincent Dutordoir
Traditional denoising diffusion models are defined on finite-dimension Euclidean spaces (Song and Ermon, 2019; Song et al., 2021; Ho et al., 2020; Dhariwal and Nichol, 2021).
Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models
We conduct extensive experiments on various benchmark datasets, empirically demonstrate the effectiveness of Terra.
Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees Y u Gui
Before deploying outputs from foundation models in high-stakes tasks, it is imperative to ensure that they align with human values.
HybridMambaforFew-ShotSegmentation
Manyfew-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity.
Towards Symmetry-Aware Generation of Periodic Materials
We consider the problem of generating periodic materials with deep models.