Wonmin Byeon ![](/sites/default/files/person/byeon.png) Research Area(s) [Computer Vision](/index.php/research-area/computer-vision) [Robotics](/index.php/research-area/robotics) Main Field of Interest [Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence) ### Publications ### 2026 [Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting](/publication/2026-01_demystifying-data-driven-probabilistic-medium-range-weather-forecasting) [Jean Kossaifi](/person/jean-kossaifi), [Nikola Kovachki](/person/nikola-kovachki), [Morteza Mardani](/person/morteza-mardani), [Daniel Leibovici](/person/daniel-leibovici), Suman Ravuri, Ira Shokar, Edoardo Calvello, Mohammad Shoaib Abbas, Peter Harrington, Ashay Subramaniam, [Noah Brenowitz](/person/noah-brenowitz), [Boris Bonev](/person/boris-bonev), [Wonmin Byeon](/person/wonmin-byeon), [Karsten Kreis](/person/karsten-kreis), [Dale Durran](/person/dale-durran), [Arash Vahdat](/person/arash-vahdat), [Mike Pritchard](/person/mike-pritchard), [Jan Kautz](/person/jan-kautz) ### 2025 [Hymba: A Hybrid-head Architecture for Small Language Models](/publication/2025-04_hymba-hybrid-head-architecture-small-language-models) Xin Dong, [Yonggan Fu\*](/person/yonggan-fu), Shizhe Diao, [Wonmin Byeon](/person/wonmin-byeon), Zijia Chen, Ameya Sunil Mahabaleshwarkar, Shih-Yang Liu, [Matthijs Van keirsbilck](/person/matthijs-van-keirsbilck), [Min-Hung Chen](/person/min-hung-chen), [Yoshi Nishi](/person/yoshi-nishi), Yingyan Celine Lin, [Jan Kautz](/person/jan-kautz), [Pavlo Molchanov](/person/pavlo-molchanov) [Hymba - ICLR 2025](https://jankautz.com/publications/Hymba_ICLR25.pdf) ICLR spotlight paper ### 2024 [RegionGPT: Towards Region Understanding Vision Language Model](/publication/2024-06_regiongpt-towards-region-understanding-vision-language-model) Qiushan Guo, [Shalini De Mello](/person/shalini-de-mello), [Hongxu Danny Yin](/person/danny-yin), [Wonmin Byeon](/person/wonmin-byeon), Ka Chun Cheung, Yizhou Yu, Ping Luo, [Sifei Liu](/person/sifei-liu) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024](https://openaccess.thecvf.com/content/CVPR2024/papers/Guo_RegionGPT_Towards_Region_Understanding_Vision_Language_Model_CVPR_2024_paper.pdf) [An Empirical Study of Mamba-based Language Models](/index.php/publication/2024-06_empirical-study-mamba-based-language-models) Roger Waleffe, [Wonmin Byeon](/index.php/person/wonmin-byeon), Duncan Riach, Brandon Norick, Vijay Korthikanti, Tri Dao, Albert Gu, [Ali Hatamizadeh](/index.php/person/ali-hatamizadeh), Sudhakar Singh, Deepak Narayanan, Garvit Kulshreshtha, Vartika Singh, Jared Casper, [Jan Kautz](/index.php/person/jan-kautz), Mohammad Shoeybi, Bryan Catanzaro ### 2023 [Convolutional State Space Models for Long-Range Spatiotemporal Modeling](/publication/2023-12_convolutional-state-space-models-long-range-spatiotemporal-modeling) Jimmy T. H. Smith, [Shalini De Mello](/person/shalini-de-mello), [Jan Kautz](/person/jan-kautz), Scott Linderman, [Wonmin Byeon](/person/wonmin-byeon) [Advances in Neural Information Processing Systems (NeurIPS) 2023](https://nips.cc/) [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](/publication/2023-06_open-vocabulary-panoptic-segmentation-text-image-diffusion-models) Jiarui Xu, [Sifei Liu](/person/sifei-liu), [Arash Vahdat](/person/arash-vahdat), [Wonmin Byeon](/person/wonmin-byeon), Xiaolong Wang, [Shalini De Mello](/person/shalini-de-mello) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023](https://cvpr2023.thecvf.com/) Hightlight top 10% ### 2022 [GroupViT: Semantic Segmentation Emerges from Text Supervision](/publication/2022-06_groupvit-semantic-segmentation-emerges-text-supervision) Jiarui Xu, [Shalini De Mello](/person/shalini-de-mello), [Sifei Liu](/person/sifei-liu), [Wonmin Byeon](/person/wonmin-byeon), [Thomas Breuel](/person/thomas-breuel), [Jan Kautz](/person/jan-kautz), Xiaolong Wang [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022](https://cvpr2022.thecvf.com/) [Displacement-Invariant Cost Computation for Efficient Stereo Matching](/index.php/publication/2022-01_displacement-invariant-cost-computation-efficient-stereo-matching) Yiran Zhong, [Charles Loop](/index.php/person/charles-loop), [Wonmin Byeon](/index.php/person/wonmin-byeon), [Stan Birchfield](/index.php/person/stan-birchfield), et al. [IJCV](https://link.springer.com/article/10.1007/s11263-022-01595-8) ### 2021 [Weakly-Supervised Physically Unconstrained Gaze Estimation](/publication/2021-06_weakly-supervised-physically-unconstrained-gaze-estimation) Rakshit Kothari, [Shalini De Mello](/person/shalini-de-mello), [Umar Iqbal](/person/umar-iqbal), [Wonmin Byeon](/person/wonmin-byeon), Seonwook Park, [Jan Kautz](/person/jan-kautz) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021](http://cvpr2021.thecvf.com/) Oral ### 2020 [Convolutional Tensor-Train LSTM for Spatio-Temporal Learning](/publication/2020-12_convolutional-tensor-train-lstm-spatio-temporal-learning) Jiahao Su, [Wonmin Byeon](/person/wonmin-byeon), [Jean Kossaifi](/person/jean-kossaifi), Furong Huang, [Jan Kautz](/person/jan-kautz), Anima Anandkumar [Advances in Neural Information Processing Systems (NeurIPS)](https://papers.nips.cc/paper/2020/hash/9e1a36515d6704d7eb7a30d783400e5d-Abstract.html) [Displacement-Invariant Cost Computation for Efficient Stereo Matching](/publication/2020-01_displacement-invariant-cost-computation-efficient-stereo-matching) Yiran Zhong, [Charles Loop](/person/charles-loop), [Wonmin Byeon](/person/wonmin-byeon), [Stan Birchfield](/person/stan-birchfield), Yuchao Dai, Kaihao Zhang, Alexey Kamenev, [Thomas Breuel](/person/thomas-breuel), Hongdong Li, [Jan Kautz](/person/jan-kautz) arXiv