Ming-Yu Liu ![](/sites/default/files/person/mingyu_2018.jpg) Ming-Yu Liu is a Vice President of Research at NVIDIA and a Fellow of IEEE. He leads [the Deep Imagination Research group](https://research.nvidia.com/labs/dir/) at NVIDIA, which focuses on deep generative models and their applications in content creation. [NVIDIA Cosmos](https://www.nvidia.com/en-us/ai/cosmos/), [NVIDIA Canvas \[GauGAN\]](https://www.nvidia.com/en-us/studio/canvas/) and [NVIDIA Maxine \[LivePortrait\]](https://developer.nvidia.com/maxine) are three products enabled by research from his research group. His research group constantly has scientific papers published in top-tier AI conferences, including NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, and SIGGRAPH. Several of their papers received prestigious awards. His team is taking the mission of building text2image, text2video, and text23d foundation models for NVIDIA AI Foundry. They are hiring research scientists to join their mission. If interested, please drop him an email, mingyul at nvidia dot com. Research Area(s) [Applied Perception](/index.php/research-area/applied-perception) [Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence) [Computational Photography and Imaging](/index.php/research-area/computational-photography-imaging) [Computer Graphics](/index.php/research-area/computer-graphics) [Computer Vision](/index.php/research-area/computer-vision) [Real-Time Rendering](/index.php/research-area/real-time-rendering) [VR, AR and Display Technology](/index.php/research-area/virtual-augmented-reality) Main Field of Interest [Computer Vision](/index.php/research-area/computer-vision) Google Scholar [https://scholar.google.com/citations?user=y-f-MZgAAAAJ&hl=en](https://scholar.google.com/citations?user=y-f-MZgAAAAJ&hl=en) ### Publications ### 2025 [World Simulation With Video Foundation Models for Physical AI](/index.php/publication/2025-09_world-simulation-video-foundation-models-physical-ai) [Ming-Yu Liu](/index.php/person/ming-yu-liu), [Cosmos Transfer 1: World-to-World Transfer with Adaptive Multi-Control for Physical AI](/publication/2025-03_cosmos-transfer-1-world-world-transfer-adaptive-multi-control-physical-ai) [Ming-Yu Liu](/person/ming-yu-liu) [Arxiv](https://arxiv.org/abs/2503.14492) [Cosmos-Reason 1: From Physical AI Common Sense to Embodied Decisions](/publication/2025-03_cosmos-reason-1-physical-ai-common-sense-embodied-decisions) [Tsung-Yi Lin](/person/tsung-yi-lin), [Ming-Yu Liu](/person/ming-yu-liu) [Cosmos World Foundation Model Platform for Physical AI](/index.php/publication/2025-01_cosmos-world-foundation-model-platform-physical-ai) [Ming-Yu Liu](/index.php/person/ming-yu-liu), Many other contributors at https://d1qx31qr3h6wln.cloudfront.net/publications/NVIDIA%20Cosmos_4.pdf, [Jing Zhang](/index.php/person/jing-zhang) ### 2023 [ATT3D: Amortized Text-To-3D Object Synthesis](/index.php/publication/2023-10_att3d-amortized-text-3d-object-synthesis) Jonathan Lorraine, Kevin Xie, Xiaohui Zeng, [Chen-Hsuan Lin](/index.php/person/chen-hsuan-lin), Towaki Takikawa, Nicholas Sharp, [Tsung-Yi Lin](/index.php/person/tsung-yi-lin), [Ming-Yu Liu](/index.php/person/ming-yu-liu), Sanja Fidler, James Lucas [ICCV](https://openaccess.thecvf.com/content/ICCV2023/papers/Lorraine_ATT3D_Amortized_Text-to-3D_Object_Synthesis_ICCV_2023_paper.pdf) [Neuralangelo: High-Fidelity Neural Surface Reconstruction](/publication/2023-06_neuralangelo-high-fidelity-neural-surface-reconstruction) [Max Zhaoshuo Li](/person/max-zhaoshuo-li), [Thomas Müller](/person/thomas-muller), Alex Evans, Russell H. Taylor, Mathias Unberath, [Ming-Yu Liu](/person/ming-yu-liu), [Chen-Hsuan Lin](/person/chen-hsuan-lin) [CVPR 2023](https://cvpr2023.thecvf.com/) The Best Inventions of 2023, TIME Magazine [Magic3D: High-Resolution Text-to-3D Content Creation](/publication/2023-06_magic3d-high-resolution-text-3d-content-creation) [Chen-Hsuan Lin](/person/chen-hsuan-lin), Jun Gao, Luming Tang, Towaki Takikawa, Xiaohui Zeng, Xun Huang, [Karsten Kreis](/person/karsten-kreis), Sanja Fidler, [Ming-Yu Liu](/person/ming-yu-liu), [Tsung-Yi Lin](/person/tsung-yi-lin) [CVPR 2023 (Highlight)](https://cvpr2023.thecvf.com/) ### 2022 [LNS-Madam: Low-Precision Training in Logarithmic Number System Using Multiplicative Weight Update](/publication/2022-12_lns-madam-low-precision-training-logarithmic-number-system-using-multiplicative) Jiawei Zhao, [Steve Dai](/person/steve-dai), [Rangharajan Venkatesan](/person/rangharajan-venkatesan), [Brian Zimmer](/person/brian-zimmer), Mustafa Ali, [Ming-Yu Liu](/person/ming-yu-liu), [Brucek Khailany](/person/brucek-khailany), [William Dally](/person/william-dally), Anima Anandkumar [IEEE Transactions on Computers (Volume: 71, Issue: 12, 01 December 2022)](https://www.computer.org/csdl/journal/tc) ### 2021 [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](/publication/2021-06_one-shot-free-view-neural-talking-head-synthesis-video-conferencing) [Ting-Chun Wang](/person/ting-chun-wang), Arun Mallya, [Ming-Yu Liu](/person/ming-yu-liu) [CVPR](https://cvpr2021.thecvf.com/) ### 2020 [UNAS: Differentiable Architecture Search Meets Reinforcement Learning](/publication/2020-08_unas-differentiable-architecture-search-meets-reinforcement-learning) [Arash Vahdat](/person/arash-vahdat), Arun Mallya, [Ming-Yu Liu](/person/ming-yu-liu), [Jan Kautz](/person/jan-kautz) [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021](https://arxiv.org/abs/1912.07651) [UFO2: A Unified Framework towards Omni-supervised Object Detection](/publication/2020-08_ufo2-unified-framework-towards-omni-supervised-object-detection) Zhongzheng Ren, [Zhiding Yu](/person/zhiding-yu), Xiaodong Yang, [Ming-Yu Liu](/person/ming-yu-liu), Alexander G. Schwing, [Jan Kautz](/person/jan-kautz) [European Conference on Computer Vision (ECCV) 2020](https://eccv2020.eu/) [World-Consistent Video-to-Video Synthesis](/publication/2020-08_world-consistent-video-video-synthesis) Arun Mallya, [Ting-Chun Wang](/person/ting-chun-wang), Karan Sapra, [Ming-Yu Liu](/person/ming-yu-liu) [ECCV](https://eccv2020.eu/) [Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection](/publication/2020-06_instance-aware-context-focused-and-memory-efficient-weakly-supervised-object) Zhongzheng Ren, [Zhiding Yu](/person/zhiding-yu), Xiaodong Yang, [Ming-Yu Liu](/person/ming-yu-liu), Yong Jae Lee, Alexander G. Schwing, [Jan Kautz](/person/jan-kautz) [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020](http://cvpr2020.thecvf.com/) [SymGAN: Orientation Estimation without Annotation for Symmetric Objects](/publication/2020-03_symgan-orientation-estimation-without-annotation-symmetric-objects) Phil Ammirato, [Jonathan Tremblay](/person/jonathan-tremblay), [Ming-Yu Liu](/person/ming-yu-liu), Alexander Berg, Dieter Fox [WACV](https://wacv20.wacv.net/) [On the Distance between Two Neural Networks and the Stability of Learning](/publication/2020-02_distance-between-two-neural-networks-and-stability-learning) Jeremy Bernstein, [Arash Vahdat](/person/arash-vahdat), Yisong Yue, [Ming-Yu Liu](/person/ming-yu-liu) [Neural Information Processing Systems (NeurIPS) 2020](https://arxiv.org/abs/2002.03432) [Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation](/publication/2020-01_domain-stylization-fast-covariance-matching-framework-towards-domain-adaptation) Aysegul Dundar, [Ming-Yu Liu](/person/ming-yu-liu), [Zhiding Yu](/person/zhiding-yu), [Ting-Chun Wang](/person/ting-chun-wang), John Zedlewski, [Jan Kautz](/person/jan-kautz) [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34) ### 2019 [Few-Shot Video-to-Video Synthesis](/publication/2019-12_few-shot-video-video-synthesis) [Ting-Chun Wang](/person/ting-chun-wang), [Ming-Yu Liu](/person/ming-yu-liu), Andrew Tao, Guilin Liu, [Jan Kautz](/person/jan-kautz), Bryan Catanzaro [NeurIPS](https://www.nips.cc/) [Dance to Music](/publication/2019-12_dance-music) Hsin-Ying Lee, [Xiaodong Yang](/person/xiaodong-yang), [Ming-Yu Liu](/person/ming-yu-liu), [Ting-Chun Wang](/person/ting-chun-wang), Yu-Ding Lu, Ming-Hsuan Yang, [Jan Kautz](/person/jan-kautz) [NeurIPS](https://www.nips.cc) [Few-Shot Unsupervised Image-to-Image Translation](/publication/2019-10_few-shot-unsupervised-image-image-translation) [Ming-Yu Liu](/person/ming-yu-liu), Xun Huang, Arun Mallya, [Tero Karras](/person/tero-karras), [Timo Aila](/person/timo-aila), [Jaakko Lehtinen](/person/jaakko-lehtinen), [Jan Kautz](/person/jan-kautz) [ICCV](http://iccv2019.thecvf.com/) [Meta-Sim: Learning to Generate Synthetic Datasets](/publication/2019-10_meta-sim-learning-generate-synthetic-datasets) Amlan Kar, Aayush Prakash, [Ming-Yu Liu](/person/ming-yu-liu), Eric Cameracci, Justin Yuan, Matt Rusiniak, David Acuna, Antonio Torralba, Sanja Fidler [ICCV](http://iccv2019.thecvf.com/) [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](/index.php/publication/2019-10_pointflow-3d-point-cloud-generation-continuous-normalizing-flows) Guandao Yang, Xun Huang, Zekun Hao, [Ming-Yu Liu](/index.php/person/ming-yu-liu), Serge Belongie, Bharath Hariharan [ICCV](http://iccv2019.thecvf.com/) [Neural Turtle Graphics for Modeling City Road Layouts](/index.php/publication/2019-10_neural-turtle-graphics-modeling-city-road-layouts) Hang Chu, Daiqing Li, David Acuna, Amlan Kar, Maria Shugrina, Xinkai Wei, [Ming-Yu Liu](/index.php/person/ming-yu-liu), Antonio Torralba, Sanja Fidler [ICCV](http://iccv2019.thecvf.com/) [CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification](/index.php/publication/2019-06_cityflow-city-scale-benchmark-multi-target-multi-camera-vehicle-tracking-and-re) Zheng Tang, Milind Naphade, [Ming-Yu Liu](/index.php/person/ming-yu-liu), [Xiaodong Yang](/index.php/person/xiaodong-yang), [Stan Birchfield](/index.php/person/stan-birchfield), Shuo Wang, Ratnesh Kumar, David Anastasiu, Jenq-Neng Hwan [CVPR 2019](http://cvpr2019.thecvf.com/) [Semantic Image Synthesis with Spatially-Adaptive Normalization](/index.php/publication/2019-06_semantic-image-synthesis-spatially-adaptive-normalization) Taesung Park, [Ming-Yu Liu](/index.php/person/ming-yu-liu), [Ting-Chun Wang](/index.php/person/ting-chun-wang), Jun-Yan Zhu [CVPR](http://cvpr2019.thecvf.com/) [STEP: Spatio-Temporal Progressive Learning for Video Action Detection](/publication/2019-06_step-spatio-temporal-progressive-learning-video-action-detection) Xitong Yang, [Xiaodong Yang](/person/xiaodong-yang), [Ming-Yu Liu](/person/ming-yu-liu), Fanyi Xiao, Larry Davis, [Jan Kautz](/person/jan-kautz) [CVPR](http://cvpr2019.thecvf.com/) [Unsupervised Stylish Image Description Generation via Domain Layer Norm](/publication/2019-02_unsupervised-stylish-image-description-generation-domain-layer-norm) Cheng-Kuan Chen, Zhu-Feng Pan, [Ming-Yu Liu](/person/ming-yu-liu), Min Sun [AAAI](https://aaai.org/Conferences/AAAI-19/) [Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation](/publication/2019-01_models-matter-so-does-training-empirical-study-cnns-optical-flow-estimation) Deqing Sun, [Xiaodong Yang](/person/xiaodong-yang), [Ming-Yu Liu](/person/ming-yu-liu), [Jan Kautz](/person/jan-kautz) [TPAMI](https://ieeexplore.ieee.org/document/8621052) ### 2018 [Localization-Aware Active Learning for Object Detection](/index.php/publication/2018-12_localization-aware-active-learning-object-detection) Chieh-Chi Kao, Teng-Yok Lee, Pradeep Sen, [Ming-Yu Liu](/index.php/person/ming-yu-liu) [ACCV](https://arxiv.org/pdf/1801.05124.pdf) [Context-aware Synthesis and Placement of Object Instances](/index.php/publication/2018-12_context-aware-synthesis-and-placement-object-instances) Donghoon Lee, [Sifei Liu](/index.php/person/sifei-liu), Jinwei Gu, [Ming-Yu Liu](/index.php/person/ming-yu-liu), Ming-Hsuan Yang, [Jan Kautz](/index.php/person/jan-kautz) NIPS [Video-to-Video Synthesis](/index.php/publication/2018-12_video-video-synthesis) [Ting-Chun Wang](/index.php/person/ting-chun-wang), [Ming-Yu Liu](/index.php/person/ming-yu-liu), Jun-Yan Zhu, Guilin Liu, Andrew Tao, [Jan Kautz](/index.php/person/jan-kautz), Bryan Catanzaro [NIPS](https://arxiv.org/abs/1808.06601) [A Closed-form Solution to Photorealistic Image Stylization](/index.php/publication/2018-09_closed-form-solution-photorealistic-image-stylization) Yijun Li, [Ming-Yu Liu](/index.php/person/ming-yu-liu), Xueting Li, Ming-Hsuan Yang, [Jan Kautz](/index.php/person/jan-kautz) [ECCV](http://arxiv.org/abs/1802.06474) [Multimodal Unsupervised Image-to-Image Translation](/publication/2018-09_multimodal-unsupervised-image-image-translation) Xun Huang, [Ming-Yu Liu](/person/ming-yu-liu), Serge Belongie, [Jan Kautz](/person/jan-kautz) [ECCV](https://arxiv.org/abs/1804.04732) [Superpixel Sampling Networks](/index.php/publication/2018-09_superpixel-sampling-networks) Varun Jampani, Deqing Sun, [Ming-Yu Liu](/index.php/person/ming-yu-liu), Ming-Hsuan Yang, [Jan Kautz](/index.php/person/jan-kautz) [European Conference on Computer Vision (ECCV), 2018](http://eccv2018.org) [Learning Superpixels with Segmentation-Aware Affinity Losse](/publication/2018-06_learning-superpixels-segmentation-aware-affinity-losse) Wei-Chih Tu, [Ming-Yu Liu](/person/ming-yu-liu), Varun Jampani, Deqing Sun, Shao-Yi Chien, Ming-Hsuan Yang, [Jan Kautz](/person/jan-kautz) [CVPR](https://ieeexplore.ieee.org/document/8578164) [MoCoGAN: Decomposing Motion and Content for Video Generation](/publication/2018-06_mocogan-decomposing-motion-and-content-video-generation) Sergey Tulyakov, [Ming-Yu Liu](/person/ming-yu-liu), [Xiaodong Yang](/person/xiaodong-yang), [Jan Kautz](/person/jan-kautz) [CVPR](https://arxiv.org/abs/1707.04993) [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](/index.php/publication/2018-06_pwc-net-cnns-optical-flow-using-pyramid-warping-and-cost-volume) Deqing Sun, [Xiaodong Yang](/index.php/person/xiaodong-yang), [Ming-Yu Liu](/index.php/person/ming-yu-liu), [Jan Kautz](/index.php/person/jan-kautz) [CVPR](http://cvpr2018.thecvf.com/) [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](/index.php/publication/2018-06_high-resolution-image-synthesis-and-semantic-manipulation-conditional-gans) [Ting-Chun Wang](/index.php/person/ting-chun-wang), [Ming-Yu Liu](/index.php/person/ming-yu-liu), Jun-Yan Zhu, Andrew Tao, [Jan Kautz](/index.php/person/jan-kautz), Bryan Catanzaro [CVPR](https://arxiv.org/abs/1711.11585) [Reblur2Deblur: Deblurring Videos via Self-Supervised Learning](/publication/2018-05_reblur2deblur-deblurring-videos-self-supervised-learning) Huaijin Chen, [Jinwei Gu](/person/jinwei-gu), Orazio Gallo, [Ming-Yu Liu](/person/ming-yu-liu), Ashok Veeraraghavan, [Jan Kautz](/person/jan-kautz) [IEEE International Conference on Computational Photography (ICCP)](http://iccp2018.ece.cmu.edu/) [Learning Binary Residual Representations for Domain-specific Video Streaming](/publication/2018-02_learning-binary-residual-representations-domain-specific-video-streaming) Yi-Hsuan Tsai, [Ming-Yu Liu](/person/ming-yu-liu), Deqing Sun, Ming-Hsuan Yang, [Jan Kautz](/person/jan-kautz) [AAAI](https://aaai.org/Conferences/AAAI-18/) ### 2017 [Unsupervised Image-to-Image Translation Networks](/index.php/publication/2017-12_unsupervised-image-image-translation-networks) [Ming-Yu Liu](/index.php/person/ming-yu-liu), [Thomas Breuel](/index.php/person/thomas-breuel), [Jan Kautz](/index.php/person/jan-kautz) [NIPS](https://nips.cc/) [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](/publication/2017-08_tactics-adversarial-attack-deep-reinforcement-learning-agents) Yen-Chen Lin, Zhang-Wei Hong, Yuan-Hong Liao , Meng-Li Shi, [Ming-Yu Liu](/person/ming-yu-liu), Min Sun [IJCAI](https://ijcai-17.org/) [Deep 360 Pilot: Learning a Deep Agent for Piloting through 360 Sports Videos](/index.php/publication/2017-07_deep-360-pilot-learning-deep-agent-piloting-through-360-sports-videos) Hou-Ning Hu, Yen-Chen Lin, [Ming-Yu Liu](/index.php/person/ming-yu-liu), Hsien-Tzu Cheng, Yung-Ju Chang, Min Sun [CVPR](http://cvpr2017.thecvf.com/)