Stephen Tyree ![](/sites/default/files/person/5M3A5458cropresize.jpeg) Stephen joined the Learning and Perception group at NVIDIA Research in 2015 and has worked in the areas of deep learning, computer vision, and robotics. He completed his Ph.D. in Computer Science at Washington University in St. Louis (St. Louis, MO, USA) in December 2014. He holds a Bachelors degree in computer science and mathematics and a Masters degree in computer science, both from the University of Tulsa (Tulsa, OK, USA). Research Area(s) [Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence) [Computer Vision](/research-area/computer-vision) [Robotics](/research-area/robotics) Main Field of Interest [Computer Vision](/research-area/computer-vision) Google Scholar [https://scholar.google.com/citations?hl=en&user=PGZLZFUAAAAJ](https://scholar.google.com/citations?hl=en&user=PGZLZFUAAAAJ) ### Publications ### 2025 [Towards a VLM Benchmark for Simulated Robotics](/publication/2025-06_towards-vlm-benchmark-simulated-robotics) [Xuning Yang](/person/xuning-yang), Clemens Eppner, [Valts Blukis](/person/valts-blukis), [Peter Belcak](/person/peter-belcak), [Stephen Tyree](/person/stephen-tyree), [Stan Birchfield](/person/stan-birchfield), [Fabio Ramos](/person/fabio-ramos), [Jonathan Tremblay](/person/jonathan-tremblay) [RSS 2025 Workshop on Large Foundation Models for Interactive Robot Learning](https://lfmrss2025.weebly.com/) [RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics](/publication/2025-06_robospatial-teaching-spatial-understanding-2d-and-3d-vision-language-models) Chan Hee Song, [Valts Blukis](/person/valts-blukis), [Jonathan Tremblay](/person/jonathan-tremblay), [Stephen Tyree](/person/stephen-tyree), Yu Su, [Stan Birchfield](/person/stan-birchfield) [CVPR 2025](https://cvpr.thecvf.com/) ### 2023 [HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions](/publication/2023-10_handal-dataset-real-world-manipulable-object-categories-pose-annotations) Andrew Guo, [Bowen Wen](/person/bowen-wen), Jianhe Yuan, [Jonathan Tremblay](/person/jonathan-tremblay), [Stephen Tyree](/person/stephen-tyree), [Jeff Smith](/person/jeff-smith), [Stan Birchfield](/person/stan-birchfield) [IROS 2023](https://ieee-iros.org/) [BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects](/publication/2023-06_bundlesdf-neural-6-dof-tracking-and-3d-reconstruction-unknown-objects) [Bowen Wen](/person/bowen-wen), [Jonathan Tremblay](/person/jonathan-tremblay), [Valts Blukis](/person/valts-blukis), [Stephen Tyree](/person/stephen-tyree), [Thomas Müller](/person/thomas-muller), Alex Evans, Dieter Fox, [Jan Kautz](/person/jan-kautz), [Stan Birchfield](/person/stan-birchfield) [CVPR 2023](https://cvpr2023.thecvf.com/) [Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation](/index.php/publication/2023-05_parallel-inversion-neural-radiance-fields-robust-pose-estimation) Yunzhi Lin, [Thomas Müller](/index.php/person/thomas-muller), [Jonathan Tremblay](/index.php/person/jonathan-tremblay), [Bowen Wen](/index.php/person/bowen-wen), [Stephen Tyree](/index.php/person/stephen-tyree), Alex Evans, Patricio A. Vela, [Stan Birchfield](/index.php/person/stan-birchfield) [ICRA 2023](https://www.icra2023.org/) [RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control ](/publication/2023-05_rgb-only-reconstruction-tabletop-scenes-collision-free-manipulator-control) Zhenggang Tang, [Balakumar Sundaralingam](/person/balakumar-sundaralingam), [Jonathan Tremblay](/person/jonathan-tremblay), [Bowen Wen](/person/bowen-wen), [Ye Yuan](/person/ye-yuan), [Stephen Tyree](/person/stephen-tyree), [Charles Loop](/person/charles-loop), Alexander Schwing, [Stan Birchfield](/person/stan-birchfield) [ICRA 2023](https://www.icra2023.org/) ### 2022 [MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare](/publication/2022-12_megapose-6d-pose-estimation-novel-objects-render-compare) Yann Labbe, Lucas Manuelli, Arsalan Mousavian, [Stephen Tyree](/person/stephen-tyree), [Stan Birchfield](/person/stan-birchfield), [Jonathan Tremblay](/person/jonathan-tremblay), et al. [CoRL 2022](https://corl2022.org/) [6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark](/publication/2022-11_6-dof-pose-estimation-household-objects-robotic-manipulation-accessible-dataset) [Stephen Tyree](/person/stephen-tyree), [Jonathan Tremblay](/person/jonathan-tremblay), [Stan Birchfield](/person/stan-birchfield), et al. [IROS 2022](https://iros2022.org/) [Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image](/publication/2022-02_single-stage-keypoint-based-category-level-object-pose-estimation-rgb-image) Yunzhi Lin, [Jonathan Tremblay](/person/jonathan-tremblay), [Stephen Tyree](/person/stephen-tyree), Patricio A. Vela, [Stan Birchfield](/person/stan-birchfield) ICRA 2022 [Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation](/publication/2022-01_keypoint-based-category-level-object-pose-tracking-rgb-sequence-uncertainty) Yunzhi Lin, [Jonathan Tremblay](/person/jonathan-tremblay), [Stephen Tyree](/person/stephen-tyree), Patricio A. Vela, [Stan Birchfield](/person/stan-birchfield) ICRA 2022 ### 2021 [Multi-View Fusion for Multi-Level Robotic Scene Understanding](/publication/2021-09_multi-view-fusion-multi-level-robotic-scene-understanding) Yunzhi Lin, [Jonathan Tremblay](/person/jonathan-tremblay), [Stephen Tyree](/person/stephen-tyree), Patricio A. Vela, [Stan Birchfield](/person/stan-birchfield) [IROS 2021](https://www.iros2021.org/) [NViSII: A Scriptable Tool for Photorealistic Image Generation](/publication/2021-05_nvisii-scriptable-tool-photorealistic-image-generation) Nathan Morrical, [Jonathan Tremblay](/person/jonathan-tremblay), Yunzhi Lin, [Stephen Tyree](/person/stephen-tyree), [Stan Birchfield](/person/stan-birchfield), Valerio Pascucci, Ingo Wald SDG Workshop at ICLR 2021 ### 2020 [Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera](/publication/2020-07_indirect-object-robot-pose-estimation-external-monocular-rgb-camera) [Jonathan Tremblay](/person/jonathan-tremblay), [Stephen Tyree](/person/stephen-tyree), Terry Mosier, [Stan Birchfield](/person/stan-birchfield) IROS 2020 [How to close sim-real gap? transfer with segmentation!](/publication/2020-05_how-close-sim-real-gap-transfer-segmentation) Mengyuan Yan, Qingyun Sun, [Iuri Frosio](/person/iuri-frosio), [Stephen Tyree](/person/stephen-tyree), [Jan Kautz](/person/jan-kautz) arxiv ### 2019 [Importance Estimation for Neural Network Pruning](/publication/2019-06_importance-estimation-neural-network-pruning) [Pavlo Molchanov](/person/pavlo-molchanov), Arun Mallya, [Stephen Tyree](/person/stephen-tyree), [Iuri Frosio](/person/iuri-frosio), [Jan Kautz](/person/jan-kautz) CVPR2019 ### 2018 [Improving Landmark Localization with Semi-Supervised Learning](/index.php/publication/2018-06_improving-landmark-localization-semi-supervised-learning) Sina Honari, [Pavlo Molchanov](/index.php/person/pavlo-molchanov), [Stephen Tyree](/index.php/person/stephen-tyree), Pascal Vincent, Christopher Pal, [Jan Kautz](/index.php/person/jan-kautz) [CVPR](http://cvpr2018.thecvf.com) [Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations ](/publication/2018-05_synthetically-trained-neural-networks-learning-human-readable-plans-real-world) [Jonathan Tremblay](/person/jonathan-tremblay), Thang To, Artem Molchanov, [Stephen Tyree](/person/stephen-tyree), [Jan Kautz](/person/jan-kautz), [Stan Birchfield](/person/stan-birchfield) [IEEE International Conference on Robotics and Automation (ICRA) 2018](https://icra2018.org/) ### 2017 [Sim-to-Real Transfer of Accurate Grasping with Eye-In-Hand Observations and Continuous Control](/index.php/publication/2017-12_sim-real-transfer-accurate-grasping-eye-hand-observations-and-continuous) Mengyuan Yan, [Iuri Frosio](/index.php/person/iuri-frosio), [Stephen Tyree](/index.php/person/stephen-tyree), [Jan Kautz](/index.php/person/jan-kautz) [NIPS 2017 Workshop on Acting and Interacting in the Real World: Challenges in …](https://sites.google.com/view/nips17robotlearning/home) [A Lightweight Approach for On-the-Fly Reflectance Estimation](/index.php/publication/2017-10_lightweight-approach-fly-reflectance-estimation) Kihwan Kim, [Jinwei Gu](/index.php/person/jinwei-gu), [Stephen Tyree](/index.php/person/stephen-tyree), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Matthias Nießner, [Jan Kautz](/index.php/person/jan-kautz) [IEEE International Conference on Computer Vision (ICCV 2017)](http://iccv2017.thecvf.com/) [Pruning Convolutional Neural Networks for Resource Efficient Inference](/publication/2017-04_pruning-convolutional-neural-networks-resource-efficient-inference) [Pavlo Molchanov](/person/pavlo-molchanov), [Stephen Tyree](/person/stephen-tyree), [Tero Karras](/person/tero-karras), [Timo Aila](/person/timo-aila), [Jan Kautz](/person/jan-kautz) [International Conference on Learning Representations (ICLR 2017)](https://openreview.net/forum?id=SJGCiw5gl¬eId=SJGCiw5gl) [Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU](/index.php/publication/2017-04_reinforcement-learning-through-asynchronous-advantage-actor-critic-gpu) [Iuri Frosio](/index.php/person/iuri-frosio), [Stephen Tyree](/index.php/person/stephen-tyree), [Jason Clemons](/index.php/person/jason-clemons), [Jan Kautz](/index.php/person/jan-kautz), Mohammad Babaeizadeh [Proceeding of ICLR 2017](https://openreview.net/pdf?id=r1VGvBcxl) ### 2016 [Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU](/index.php/publication/2016-11_reinforcement-learning-through-asynchronous-advantage-actor-critic-gpu) Mohammad Babaeizadeh, [Iuri Frosio](/index.php/person/iuri-frosio), [Stephen Tyree](/index.php/person/stephen-tyree), [Jason Clemons](/index.php/person/jason-clemons), [Jan Kautz](/index.php/person/jan-kautz) [arXiv](https://arxiv.org/abs/1611.06256) [Towards Selecting Robust Hand Gestures for Automotive Interfaces](/index.php/publication/2016-06_towards-selecting-robust-hand-gestures-automotive-interfaces-0) [Shalini Gupta](/index.php/person/shalini-de-mello), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Xiaodong Yang, [Stephen Tyree](/index.php/person/stephen-tyree), [Jan Kautz](/index.php/person/jan-kautz) [IEEE Intelligent Vehicles Symposium (IV) 2016](http://iv2016.org/) [Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks ](/publication/2016-06_online-detection-and-classification-dynamic-hand-gestures-recurrent-3d) [Pavlo Molchanov](/person/pavlo-molchanov), [Xiaodong Yang](/person/xiaodong-yang), [Shaline Gupta](/person/shalini-de-mello), Kihwan Kim, [Stephen Tyree](/person/stephen-tyree), [Jan Kautz](/person/jan-kautz) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016](http://cvpr2016.thecvf.com/) [Towards Selecting Robust Hand Gestures for Automotive Interfaces ](/publication/2016-06_towards-selecting-robust-hand-gestures-automotive-interfaces) Shalini Gupta, [Pavlo Molchanov](/person/pavlo-molchanov), [Xiaodong Yang](/person/xiaodong-yang), Kihwan Kim, [Stephen Tyree](/person/stephen-tyree), [Jan Kautz](/person/jan-kautz) [IEEE Intelligent Vehicles Symposium](http://iv2016.org/) ### 2015 [Compressing Neural Networks with the Hashing Trick](/publication/2015-07_compressing-neural-networks-hashing-trick) Wenlin Chen, James T. Wilson, [Stephen Tyree](/person/stephen-tyree), Kilian Q. Weinberger, Yixin Chen [Proceedings of The 32nd International Conference on Machine Learning](http://jmlr.org/proceedings/papers/v37/)