Interesting Engineering

New adaptive system lets robots replicate human touch with far less training data

Researchers in Japan have developed an adaptive motion reproduction system that allows robots to generate human-like movements using surprisingly small amounts of training data. Despite rapid advances ...
IEEE

Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems

Abstract: Gaussian process state-space models (GPSSMs) offer a principled framework for learning and inference in nonlinear dynamical systems with uncertainty quantification. However, existing GPSSMs ...
eLife

Learning sequence-function relationships with scalable, interpretable Gaussian processes

This important work introduces a family of interpretable Gaussian process models that allows us to learn and model sequence-function relationships in biomolecules. These models are applied to three ...
GitHub

A minimal, portable Gaussian Splatting sandbox for rapid small-scale experimentation and performance insights in pure Python.

Gaussian Splatting is a cutting-edge 3D representation technique that models a scene as a set of learnable 3D Gaussian primitives. Each Gaussian defines a point in space with position, color, opacity, ...
GitHub

Installation fails for diff-gaussian-rasterization-w-pose on Python 3.10 / NumPy 2.x / pip 25+

Hi, I’m trying to set up GaussianObject on Ubuntu 22.04 with Python 3.10 and CUDA 11.8. Created a virtual environment Installed PyTorch 2.2.0 + CUDA 11.8 Installed ...
Scientific Research Publishing

Rasmussen, C.E. and Williams, C.K.I. (2005) Gaussian Processes for Machine Learning. The MIT Press.

ABSTRACT: This paper introduces a method to develop a common model based on machine learning (ML) that predicts the mechanical behavior of a family with three composite materials. The latter are ...
C&EN

Efficient Implementation of Gaussian Process Regression Accelerated Saddle Point Searches with Application to Molecular Reactions

Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to ...