Zobrazeno 1 - 10
of 8 320
pro vyhledávání: '"FENG, LIANG"'
Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by un
Externí odkaz:
http://arxiv.org/abs/2412.00534
The Lorentz reciprocity is a fundamental property in electromagnetism and well known to break down due to an external magnetic field. With a fictitious or imaginary vector potential, however, its behavior is largely unknown. Here we show that in syst
Externí odkaz:
http://arxiv.org/abs/2410.02041
Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to bypass the n
Externí odkaz:
http://arxiv.org/abs/2409.18893
This paper introduces GateAttentionPose, an innovative approach that enhances the UniRepLKNet architecture for pose estimation tasks. We present two key contributions: the Agent Attention module and the Gate-Enhanced Feedforward Block (GEFB). The Age
Externí odkaz:
http://arxiv.org/abs/2409.07798
Pose estimation is a crucial task in computer vision, with wide applications in autonomous driving, human motion capture, and virtual reality. However, existing methods still face challenges in achieving high accuracy, particularly in complex scenes.
Externí odkaz:
http://arxiv.org/abs/2409.07752
Evolutionary Multi-task Optimization (EMTO) is a paradigm that leverages knowledge transfer across simultaneously optimized tasks for enhanced search performance. To facilitate EMTO's performance, various knowledge transfer models have been developed
Externí odkaz:
http://arxiv.org/abs/2409.04270
Transferable neural architecture search (TNAS) has been introduced to design efficient neural architectures for multiple tasks, to enhance the practical applicability of NAS in real-world scenarios. In TNAS, architectural knowledge accumulated in pre
Externí odkaz:
http://arxiv.org/abs/2408.11330
Expensive optimization problems (EOPs) have attracted increasing research attention over the decades due to their ubiquity in a variety of practical applications. Despite many sophisticated surrogate-assisted evolutionary algorithms (SAEAs) that have
Externí odkaz:
http://arxiv.org/abs/2408.07176
Autor:
Yang, Zhicheng, Wang, Yiwei, Huang, Yinya, Guo, Zhijiang, Shi, Wei, Han, Xiongwei, Feng, Liang, Song, Linqi, Liang, Xiaodan, Tang, Jing
Large language models (LLMs) have exhibited their problem-solving abilities in mathematical reasoning. Solving realistic optimization (OPT) problems in application scenarios requires advanced and applied mathematics ability. However, current OPT benc
Externí odkaz:
http://arxiv.org/abs/2407.09887
Evolutionary multitasking (EMT) is an emerging approach for solving multitask optimization problems (MTOPs) and has garnered considerable research interest. The implicit EMT is a significant research branch that utilizes evolution operators to enable
Externí odkaz:
http://arxiv.org/abs/2406.14359