activity
20182021
most citedSafe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces

10 citations · 10 across the 2 of their papers we have counts for

collaborators

10 papers

cs.LG202110 cited

Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces

Ziyad Sheebaelhamd, Konstantinos Zisis, Athina Nisioti +3

Multi-agent control problems constitute an interesting area of application for deep reinforcement learning models with continuous action spaces. Such real-world applications, howev…

cs.LG2021

Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks

Antonio Orvieto, Jonas Kohler, Dario Pavllo +2

This paper revisits the so-called vanishing gradient phenomenon, which commonly occurs in deep randomly initialized neural networks. Leveraging an in-depth analysis of neural chain…

cs.CV2021

Learning Generative Models of Textured 3D Meshes from Real-World Images

Dario Pavllo, Jonas Kohler, Thomas Hofmann +1

Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle p…

cs.CV2020

Convolutional Generation of Textured 3D Meshes

Dario Pavllo, Graham Spinks, Thomas Hofmann +2

While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control…

cs.CV2020

Hierarchical Image Classification using Entailment Cone Embeddings

Ankit Dhall, Anastasia Makarova, Octavian Ganea +3

Image classification has been studied extensively, but there has been limited work in using unconventional, external guidance other than traditional image-label pairs for training.…

cs.CV2019

Controlling Style and Semantics in Weakly-Supervised Image Generation

Dario Pavllo, Aurelien Lucchi, Thomas Hofmann

We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene. We exploit sparse sema…