Výsledky vyhledávání

Report

FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection

Autor: Liao, Xinting, Liu, Weiming, Zhou, Pengyang, Yu, Fengyuan, Xu, Jiahe, Wang, Jun, Wang, Wenjie, Chen, Chaochao, Zheng, Xiaolin

Federated learning (FL) is a promising machine learning paradigm that collaborates with client models to capture global knowledge. However, deploying FL models in real-world scenarios remains unreliable due to the coexistence of in-distribution data

Externí odkaz: http://arxiv.org/abs/2410.11397

Zobrazit plný text záznamu

Report

Executing Arithmetic: Fine-Tuning Large Language Models as Turing Machines

Autor: Lai, Junyu, Xu, Jiahe, Yang, Yao, Huang, Yunpeng, Cao, Chun, Xu, Jingwei

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing and reasoning tasks. However, their performance in the foundational domain of arithmetic remains unsatisfactory. When dealing wi

Externí odkaz: http://arxiv.org/abs/2410.07896

Zobrazit plný text záznamu

Report

Flying Calligrapher: Contact-Aware Motion and Force Planning and Control for Aerial Manipulation

Autor: Guo, Xiaofeng, He, Guanqi, Xu, Jiahe, Mousaei, Mohammadreza, Geng, Junyi, Scherer, Sebastian, Shi, Guanya

Aerial manipulation has gained interest in completing high-altitude tasks that are challenging for human workers, such as contact inspection and defect detection, etc. Previous research has focused on maintaining static contact points or forces. This

Externí odkaz: http://arxiv.org/abs/2407.05587

Zobrazit plný text záznamu

Report

PyPose: A Library for Robot Learning with Physics-based Optimization

Publikováno v: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as we

Externí odkaz: http://arxiv.org/abs/2209.15428

Zobrazit plný text záznamu