Search Results for author:
Found 6 papers, 2 papers with code
CO2: Efficient Distributed Training with Full Communication-Computation Overlap
CO2 is able to attain a high scalability even on extensive multi-node clusters constrained by very limited communication bandwidth.
Sampled Transformer for Point Sets
The sparse transformer can reduce the computational complexity of the self-attention layers to $O(n)$, whilst still being a universal approximator of continuous sequence-to-sequence functions.
SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generation
This paper addresses the problem of unsupervised parts-aware point cloud generation with learned parts-based self-similarity.
EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
We achieve this with a simple modification of the Variational Auto-Encoder which yields a joint model of the point cloud itself along with a schematic representation of it as a combination of shape primitives.
Interval-censored Hawkes processes
We propose the multi-impulse exogenous function - for when the exogenous events are observed as event time - and the latent homogeneous Poisson process exogenous function - for when the exogenous events are presented as interval-censored volumes.
Smooth and Efficient Policy Exploration for Robot Trajectory Learning
Many policy search algorithms have been proposed for robot learning and proved to be practical in real robot applications.
Robotics
