Education
- PhD in Electrical and Computer Engineering, Duke University, 2020
- MS in Electrical and Computer Engineering, Duke University, 2019
- BSE in Electrical and Computer Engineering/Biomedical Engineering, Duke University, 2015
Work experience
- Meta - Research Scientist (2020 - present)
- Fundamental AI Research (FAIR): Egocentric Computer Vision, 3D Computer Vision (2021 - present)
- Facebook AI Applied Research (FAIAR): Computer Vision (2020 - 2021)
- Duke University - Research Assistant (2015 - 2020)
- Adviser: Lawrence Carin
- Facebook - Software Engineer Intern (2019)
- Ads Core ML Modeling
- Google - Software Engineering Intern (2017)
- Cloud AI, Video Understanding
Microsoft - Software Development Engineer Intern (2014)
- Duke University - Undergraduate Research Assistant
- Advisers: Leslie Collins, Guillermo Sapiro
Selected Publications
A selection of representative work. Full publication list on Google Scholar.
SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin, Jiawei Liu, Ziqi Ma, Anushka Sagar, Bowen Song, Xiaodong Wang, Jianing Yang, Bowen Zhang, Piotr Dollár, Georgia Gkioxari, Matt Feiszli, Jitendra Malik. SAM 3D: 3Dfy Anything in Images, Computer Vision and Pattern Recognition (CVPR - Best Paper Honorable Mention) 2026. [Oral presentation][website][demo][code]
Runsen Xu, Weiyao Wang, Hao Tang, Xingyu Chen, Xiaodong Wang, Fu-Jen Chu, Dahua Lin, Matt Feiszli, Kevin J Liang. Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models, Computer Vision and Pattern Recognition (CVPR) 2026.
Jianing Yang, Alexander Sax, Kevin J Liang, Mikael Henaff, Hao Tang, Ang Cao, Joyce Chai, Franziska Meier, Matt Feiszli. Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass, Computer Vision and Pattern Recognition (CVPR) 2025. [code]
Kristen Grauman, …, Kevin J Liang, …, et. al. Ego-Exo4D: Understanding Skilled Human Activity from First-and Third-Person Perspectives, Computer Vision and Pattern Recognition (CVPR - Oral) 2024. [website][video]
Hao Tang, Kevin J Liang, Kristen Grauman, Matt Feiszli*, Weiyao Wang*. EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset, Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS D&B) 2023.
Kevin J Liang, Samrudhdhi B. Rangrej, Vladan Petrovic, Tal Hassner. Few-shot Learning with Noisy Labels, Computer Vision and Pattern Recognition (CVPR) 2022.
Nikhil Mehta, Kevin J Liang, Vinay Kumar Verma, Lawrence Carin. Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors, Artificial Intelligence and Statistics (AISTATS) 2021.
Kevin J Liang*, Weituo Hao*, Dinghan Shen, Yufan Zhou, Weizhu Chen, Changyou Chen, Lawrence Carin. MixKD: Towards Efficient Distillation of Large-scale Language Models, International Conference on Learning Representations (ICLR) 2021.
Nathan Inkawhich, Kevin J Liang, Lawrence Carin, Yiran Chen. Transferable Perturbations of Deep Feature Distributions, International Conference on Learning Representations (ICLR) 2020.
Honors & Awards
- CVPR 2026 - Best Paper Honorable Mention
- E Bayard Halsted Fellowship (2017)
- George Sherrerd III Memorial Award (2015) - Duke top undergraduate ECE award
- Da Vinci Award (2015) - Duke top undergraduate BME award
- Summa cum laude (top 5% of graduating class) (2015)
- Graduation with Departmental Distinction, Electrical and Computer Engineering (2015)
- Tau Beta Pi Scholarship (2014 - 2015)
Service
- Area Chair: NeurIPS D&B (‘22-‘24), AAAI (‘23), CVPR (‘24, ‘26), ECCV (‘26)
- Reviewer: AAAI (‘21-‘22), BMVC (‘20), CVPR (‘21-‘23, ‘25), ECCV (‘22, ‘24), ICCV (‘21, ‘23, ‘25), ICLR (‘21-‘25), ICML (‘21-‘23), NeurIPS (‘20, ‘22, ‘23), TPAMI, WACV (‘20)
- Duke Undergraduate Admissions
- Duke “Engineering a Community”: Mentor
- Duke Engineering Alumni Council: Mentor
- Duke E-Team: Mentor, ECE chair, President
Teaching
Lecturer/Instructor
- +Data Science (2018 - 2020)
- Data+: Finding Space Junk with the World’s Biggest Telescopes (2020)
- Duke Natural Language Processing School (2020)
- Duke Machine Learning School (2018, 2019)
- Infinia ML Machine Learning Bootcamp (2018)
- Duke-Tsinghua Machine Learning Summer School (2017)
- Coursera: Introduction to Machine Learning
Teaching Assistantships
- ECE 590-16: Introduction to Deep Learning (2018F)
- ECE 581: Random Signals and Noise (2017F)
- ECE 381: Fundamentals of Digital Signal Processing (2016F)
- ECE 110: Fundamentals of Electrical and Computer Engineering (2014F, 2015S)
- Math 216: Linear Algebra and Differential Equations (2012F, 2013S)
