Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Vladlen Koltun

Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data


Aug 20, 2021
Zhipeng Cai, Ozan Sener, Vladlen Koltun

* Accepted to ICCV 2021 

  Access Paper or Ask Questions

Megaverse: Simulating Embodied Agents at One Million Experiences per Second


Jul 21, 2021
Aleksei Petrenko, Erik Wijmans, Brennan Shacklett, Vladlen Koltun

* Paper published in ICML2021 

  Access Paper or Ask Questions

Habitat 2.0: Training Home Assistants to Rearrange their Habitat


Jun 28, 2021
Andrew Szot, Alex Clegg, Eric Undersander, Erik Wijmans, Yili Zhao, John Turner, Noah Maestre, Mustafa Mukadam, Devendra Chaplot, Oleksandr Maksymets, Aaron Gokaslan, Vladimir Vondrus, Sameer Dharur, Franziska Meier, Wojciech Galuba, Angel Chang, Zsolt Kira, Vladlen Koltun, Jitendra Malik, Manolis Savva, Dhruv Batra


  Access Paper or Ask Questions

Stabilizing Equilibrium Models by Jacobian Regularization


Jun 28, 2021
Shaojie Bai, Vladlen Koltun, J. Zico Kolter

* ICML 2021 Short Oral 

  Access Paper or Ask Questions

Training Graph Neural Networks with 1000 Layers


Jun 17, 2021
Guohao Li, Matthias Müller, Bernard Ghanem, Vladlen Koltun

* Accepted at ICML'2021. Code available at https://www.deepgcns.org/arch/gnn1000. Work done during Guohao Li's internship at Intel Intelligent Systems Lab 

  Access Paper or Ask Questions

A Measure of Research Taste


May 17, 2021
Vladlen Koltun, David Hafner

* Results can be explored at https://cap-measure.org/ 

  Access Paper or Ask Questions

Enhancing Photorealism Enhancement


May 10, 2021
Stephan R. Richter, Hassan Abu AlHaija, Vladlen Koltun

* Code and data available at https://github.com/intel-isl/PhotorealismEnhancement Video available at https://youtu.be/P1IcaBn3ej0 

  Access Paper or Ask Questions

Learning to drive from a world on rails


May 03, 2021
Dian Chen, Vladlen Koltun, Philipp Krähenbühl

* Code and data available at: https://dotchen.github.io/world_on_rails/ 

  Access Paper or Ask Questions

Vision Transformers for Dense Prediction


Mar 24, 2021
René Ranftl, Alexey Bochkovskiy, Vladlen Koltun

* 15 pages 

  Access Paper or Ask Questions

Probabilistic two-stage detection


Mar 12, 2021
Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl

* Code is available at https://github.com/xingyizhou/CenterNet2 

  Access Paper or Ask Questions

Large Batch Simulation for Deep Reinforcement Learning


Mar 12, 2021
Brennan Shacklett, Erik Wijmans, Aleksei Petrenko, Manolis Savva, Dhruv Batra, Vladlen Koltun, Kayvon Fatahalian

* Published as a conference paper at ICLR 2021 

  Access Paper or Ask Questions

Self-supervised Geometric Perception


Mar 04, 2021
Heng Yang, Wei Dong, Luca Carlone, Vladlen Koltun

* CVPR 2021, Oral presentation. 8 pages main results, 19 pages in total, including references and supplementary 

  Access Paper or Ask Questions

Simple multi-dataset detection


Feb 25, 2021
Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl

* code is available at https://github.com/xingyizhou/UniDet 

  Access Paper or Ask Questions

Point Transformer


Dec 16, 2020
Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun


  Access Paper or Ask Questions

Stable View Synthesis


Nov 14, 2020
Gernot Riegler, Vladlen Koltun

* https://youtu.be/gqgXIY09htI 

  Access Paper or Ask Questions

Rearrangement: A Challenge for Embodied AI


Nov 03, 2020
Dhruv Batra, Angel X. Chang, Sonia Chernova, Andrew J. Davison, Jia Deng, Vladlen Koltun, Sergey Levine, Jitendra Malik, Igor Mordatch, Roozbeh Mottaghi, Manolis Savva, Hao Su

* Authors are listed in alphabetical order 

  Access Paper or Ask Questions

Learning Quadrupedal Locomotion over Challenging Terrain


Oct 21, 2020
Joonho Lee, Jemin Hwangbo, Lorenz Wellhausen, Vladlen Koltun, Marco Hutter

* Science Robotics 2020 Vol. 5, Issue 47, eabc5986 

  Access Paper or Ask Questions

NeRF++: Analyzing and Improving Neural Radiance Fields


Oct 21, 2020
Kai Zhang, Gernot Riegler, Noah Snavely, Vladlen Koltun

* Code is available at https://github.com/Kai-46/nerfplusplus; fix a minor formatting issue in Fig. 4 

  Access Paper or Ask Questions

OpenBot: Turning Smartphones into Robots


Aug 24, 2020
Matthias Müller, Vladlen Koltun


  Access Paper or Ask Questions

Free View Synthesis


Aug 12, 2020
Gernot Riegler, Vladlen Koltun

* published at ECCV 2020, https://youtu.be/JDJPn3ZtfZs 

  Access Paper or Ask Questions

Drinking from a Firehose: Continual Learning with Web-scale Natural Language


Jul 18, 2020
Hexiang Hu, Ozan Sener, Fei Sha, Vladlen Koltun

* Source Code: https://github.com/firehose-dataset/congrad 

  Access Paper or Ask Questions

Dynamic Low-light Imaging with Quanta Image Sensors


Jul 16, 2020
Yiheng Chi, Abhiram Gnanasambandam, Vladlen Koltun, Stanley H. Chan

* Published in the 16th European Conference on Computer Vision (ECCV) 2020 

  Access Paper or Ask Questions

Scaling Imitation Learning in Minecraft


Jul 06, 2020
Artemij Amiranashvili, Nicolai Dorka, Wolfram Burgard, Vladlen Koltun, Thomas Brox


  Access Paper or Ask Questions

Scalable Differentiable Physics for Learning and Control


Jul 04, 2020
Yi-Ling Qiao, Junbang Liang, Vladlen Koltun, Ming C. Lin

* Proceedings of the 37th International Conference on Machine Learning, ICML 2020 

  Access Paper or Ask Questions

Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning


Jun 23, 2020
Aleksei Petrenko, Zhehui Huang, Tushar Kumar, Gaurav Sukhatme, Vladlen Koltun

* Paper published in ICML2020. Visualizations of trained policies can be found at https://sites.google.com/view/sample-factory 

  Access Paper or Ask Questions

Multiscale Deep Equilibrium Models


Jun 15, 2020
Shaojie Bai, Vladlen Koltun, J. Zico Kolter


  Access Paper or Ask Questions

Deep Drone Acrobatics


Jun 11, 2020
Elia Kaufmann, Antonio Loquercio, René Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza

* Robotics, Science, and Systems (RSS), 2020 
* 8 pages + 2 pages references. Video: https://youtu.be/2N_wKXQ6MXA. Code: https://github.com/uzh-rpg/deep_drone_acrobatics 

  Access Paper or Ask Questions

Auto-decoding Graphs


Jun 04, 2020
Sohil Atul Shah, Vladlen Koltun


  Access Paper or Ask Questions