Следене
Xiyao Wang
Xiyao Wang
Ph.D. in University of Maryland, College Park
Потвърден имейл адрес: umd.edu - Начална страница
Заглавие
Позовавания
Позовавания
Година
A two-branch neural network for non-homogeneous dehazing via ensemble learning
Y Yu, H Liu, M Fu, J Chen, X Wang, K Wang
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
802021
NTIRE 2021 nonhomogeneous dehazing challenge report
CO Ancuti, C Ancuti, FA Vasluianu, R Timofte
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021
672021
Transfer RL across Observation Feature Spaces via Model-Based Regularization
Y Sun, R Zheng, X Wang, A Cohen, F Huang
arXiv preprint arXiv:2201.00248, 2022
162022
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
X Wang, Y Zhou, X Liu, H Lu, Y Xu, F He, J Yoon, T Lu, F Liu, G Bertasius, ...
arXiv preprint arXiv:2401.10529, 2024
102024
Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
R Zheng*, X Wang*, H Xu, F Huang
arXiv preprint arXiv:2302.01244, 2023
82023
Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
X Wang, W Wongkamjan, F Huang
ICML 2023, 2022
82022
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
R Zheng, X Wang, Y Sun, S Ma, J Zhao, H Xu, H Daumé III, F Huang
arXiv preprint arXiv:2306.13229, 2023
7*2023
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
G Xu*, R Zheng*, Y Liang*, X Wang, Z Yuan, T Ji, Y Luo, X Liu, J Yuan, ...
arXiv preprint arXiv:2310.19668, 2023
32023
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
X Wang, R Zheng, Y Sun, R Jia, W Wongkamjan, H Xu, F Huang
arXiv preprint arXiv:2310.07220, 2023
22023
Equal Long-term Benefit Rate: Adapting Static Fairness Notions to Sequential Decision Making
Y Xu, C Deng, Y Sun, R Zheng, X Wang, J Zhao, F Huang
arXiv preprint arXiv:2309.03426, 2023
22023
Emojis Decoded: Leveraging ChatGPT for Enhanced Understanding in Social Media Communications
Y Zhou, P Xu, X Wang, X Lu, G Gao, W Ai
arXiv preprint arXiv:2402.01681, 2024
12024
Premier-TACO: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
R Zheng, Y Liang, X Wang, S Ma, H Daumé III, H Xu, J Langford, ...
arXiv preprint arXiv:2402.06187, 2024
2024
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–12