Zobrazeno 1 - 10
of 3 522
pro vyhledávání: '"Tang, Ke"'
Offering rich contexts to Large Language Models (LLMs) has shown to boost the performance in various tasks, but the resulting longer prompt would increase the computational cost and might exceed the input limit of LLMs. Recently, some prompt compress
Externí odkaz:
http://arxiv.org/abs/2409.15395
Recently, graph condensation has emerged as a prevalent technique to improve the training efficiency for graph neural networks (GNNs). It condenses a large graph into a small one such that a GNN trained on this small synthetic graph can achieve compa
Externí odkaz:
http://arxiv.org/abs/2407.11025
Autor:
Li, Bingdong, Di, Zixiang, Yang, Yanting, Qian, Hong, Yang, Peng, Hao, Hao, Tang, Ke, Zhou, Aimin
In this paper, we introduce a novel approach for large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple models, each excelling in different tasks, into a single model that
Externí odkaz:
http://arxiv.org/abs/2407.00487
Real-world applications involve various discrete optimization problems. Designing a specialized optimizer for each of these problems is challenging, typically requiring significant domain knowledge and human efforts. Hence, developing general-purpose
Externí odkaz:
http://arxiv.org/abs/2405.18884
The min-max vehicle routing problem (min-max VRP) traverses all given customers by assigning several routes and aims to minimize the length of the longest route. Recently, reinforcement learning (RL)-based sequential planning methods have exhibited a
Externí odkaz:
http://arxiv.org/abs/2405.17272
This paper focuses on solving the capacitated arc routing problem with time-dependent service costs (CARPTDSC), which is motivated by winter gritting applications. In the current literature, exact algorithms designed for CARPTDSC can only handle smal
Externí odkaz:
http://arxiv.org/abs/2406.15416
Autor:
Li, Bingdong, Di, Zixiang, Lu, Yongfan, Qian, Hong, Wang, Feng, Yang, Peng, Tang, Ke, Zhou, Aimin
Multi-objective Bayesian optimization (MOBO) has shown promising performance on various expensive multi-objective optimization problems (EMOPs). However, effectively modeling complex distributions of the Pareto optimal solutions is difficult with lim
Externí odkaz:
http://arxiv.org/abs/2405.08674
Autor:
Lu, Yongfan, Di, Zixiang, Li, Bingdong, Liu, Shengcai, Qian, Hong, Yang, Peng, Tang, Ke, Zhou, Aimin
Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural MOCO methods rely on problem decomposition to transform an MOCO problem into a series of singe-objective combinatorial o
Externí odkaz:
http://arxiv.org/abs/2405.08604
Autor:
Wang, Xiao, Tang, Ke, Dai, Xingyuan, Xu, Jintao, Du, Quancheng, Ai, Rui, Wang, Yuxiao, Gu, Weihao
In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prev
Externí odkaz:
http://arxiv.org/abs/2404.11946
Autor:
Zhang, Wenqi, Tang, Ke, Wu, Hai, Wang, Mengna, Shen, Yongliang, Hou, Guiyang, Tan, Zeqi, Li, Peng, Zhuang, Yueting, Lu, Weiming
Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. However, most LLM-based agents are designed as specific task solvers with sophisticated prompt engineering, rather than agents capable of learning and evolvin
Externí odkaz:
http://arxiv.org/abs/2402.17574