| 3d diffuser actor: Policy diffusion with 3d scene representations TW Ke, N Gkanatsios, K Fragkiadaki arXiv preprint arXiv:2402.10885, 2024 | 257 | 2024 |
| Adaptive affinity fields for semantic segmentation TW Ke, JJ Hwang, Z Liu, SX Yu Proceedings of the European conference on computer vision (ECCV), 587-602, 2018 | 251 | 2018 |
| Chaineddiffuser: Unifying trajectory diffusion and keypose prediction for robotic manipulation Z Xian, N Gkanatsios, T Gervet, TW Ke, K Fragkiadaki 7th Annual Conference on Robot Learning, 2023 | 143 | 2023 |
| Multigrid neural architectures TW Ke, M Maire, SX Yu Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2017 | 113 | 2017 |
| Universal weakly supervised segmentation by pixel-to-segment contrastive learning TW Ke, JJ Hwang, SX Yu arXiv preprint arXiv:2105.00957, 2021 | 109 | 2021 |
| A convolutional neural network-based screening tool for X-ray serial crystallography TW Ke, AS Brewster, SX Yu, D Ushizima, C Yang, NK Sauter Synchrotron Radiation 25 (3), 655-670, 2018 | 81 | 2018 |
| Diffusion-ES: Gradient-free planning with diffusion for autonomous and instruction-guided driving B Yang, H Su, N Gkanatsios, TW Ke, A Jain, J Schneider, K Fragkiadaki Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2024 | 76* | 2024 |
| Unsupervised hierarchical semantic segmentation with multiview cosegmentation and clustering transformers TW Ke, JJ Hwang, Y Guo, X Wang, SX Yu Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 70 | 2022 |
| Diffusion-tta: Test-time adaptation of discriminative models via generative feedback M Prabhudesai, TW Ke, A Li, D Pathak, K Fragkiadaki Advances in Neural Information Processing Systems 36, 17567-17583, 2023 | 53* | 2023 |
| Adversarial Structure Matching for Structured Prediction Tasks JJ Hwang, TW Ke, J Shi, SX Yu Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019 | 25* | 2019 |
| Learning hierarchical image segmentation for recognition and by recognition TW Ke, S Mo, SX Yu arXiv preprint arXiv:2210.00314, 2022 | 18 | 2022 |
| Mooney face classification and prediction by learning across tone TW Ke, XY Stella, D Whitney 2017 IEEE international conference on image processing (ICIP), 2025-2029, 2017 | 12 | 2017 |
| 3D FlowMatch Actor: Unified 3D Policy for Single-and Dual-Arm Manipulation N Gkanatsios, J Xu, M Bronars, A Mousavian, TW Ke, K Fragkiadaki arXiv preprint arXiv:2508.11002, 2025 | 6* | 2025 |
| Deep learning workflow to support in-flight processing of digital aerial imagery for wildlife population surveys TW Ke, SX Yu, MD Koneff, DL Fronczak, LJ Fara, TJ Harrison, KL Landolt, ... Plos one 19 (4), e0288121, 2024 | 5 | 2024 |
| Local pseudo-attributes for long-tailed recognition DJ Kim, TW Ke, XY Stella Pattern Recognition Letters 172, 51-57, 2023 | 5 | 2023 |
| See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation CY Hu, YS Lin, Y Lee, CH Su, JY Lee, SR Tsai, CY Lin, KW Chen, TW Ke, ... Conference on Robot Learning, 4697-4708, 2025 | 4 | 2025 |
| Contextual image parsing via panoptic segment sorting JJ Hwang, TW Ke, SX Yu Multimedia Understanding with Less Labeling on Multimedia Understanding with …, 2021 | 1 | 2021 |
| Recursive reduction net for large-scale high-dimensional data TW Ke, TL Liu 2016 IEEE International Conference on Image Processing (ICIP), 1903-1907, 2016 | 1 | 2016 |
| Implicit sparse code hashing TY Lin, TW Ke, TL Liu arXiv preprint arXiv:1512.00130, 2015 | 1 | 2015 |
| RobotArena : Scalable Robot Benchmarking via Real-to-Sim Translation Y Jangir, Y Zhang, K Yamazaki, C Zhang, KH Tu, TW Ke, L Ke, Y Bisk, ... arXiv preprint arXiv:2510.23571, 2025 | | 2025 |
Stella X. YuProfessor of EECS, University of MichiganVerified email at umich.edu
