Zobrazeno 1 - 10
of 2 414
pro vyhledávání: '"Hao,Hao"'
Expensive optimization problems (EOPs) are prevalent in real-world applications, where the evaluation of a single solution requires a significant amount of resources. In our study of surrogate-assisted evolutionary algorithms (SAEAs) in EOPs, we disc
Externí odkaz:
http://arxiv.org/abs/2412.03858
Recent learning-to-imitation methods have shown promising results in planning via imitating within the observation-action space. However, their ability in open environments remains constrained, particularly in long-horizon tasks. In contrast, traditi
Externí odkaz:
http://arxiv.org/abs/2411.18201
Autor:
Peng, Hao-Hao, Fang, Ren-Hong
We study the polarization of an electron scattered by different static potentials. The initial state of the electron is chosen as a wavepacket to construct the definite orbital angular momentum, and the final polarization of the electron, scattered b
Externí odkaz:
http://arxiv.org/abs/2411.13034
Autor:
Hao, Hao, Zhang, Peter
Robust optimization provides a principled and unified framework to model many problems in modern operations research and computer science applications, such as risk measures minimization and adversarially robust machine learning. To use a robust solu
Externí odkaz:
http://arxiv.org/abs/2410.02123
We put forward a primordial scenario to alleviate cosmological tensions, i.e. Hubble ($H_0$) tension and $ S_8 $ tension. Based on flat $\Lambda$CDM, the Bounce-Inflation (BI) scenario gives the results that $ H_0 = 68.60^{+0.40}_{-0.45} \, \text{km}
Externí odkaz:
http://arxiv.org/abs/2409.04027
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 addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple models, each
Externí odkaz:
http://arxiv.org/abs/2407.00487
Large Language Models (LLMs) have achieved significant progress across various fields and have exhibited strong potential in evolutionary computation, such as generating new solutions and automating algorithm design. Surrogate-assisted selection is a
Externí odkaz:
http://arxiv.org/abs/2406.10675
Surrogate-assisted Evolutionary Algorithm (SAEA) is an essential method for solving expensive expensive problems. Utilizing surrogate models to substitute the optimization function can significantly reduce reliance on the function evaluations during
Externí odkaz:
http://arxiv.org/abs/2405.16494
Black-box optimization problems, which are common in many real-world applications, require optimization through input-output interactions without access to internal workings. This often leads to significant computational resources being consumed for
Externí odkaz:
http://arxiv.org/abs/2403.14413
This paper presents enhancements to the MT3 model, a state-of-the-art (SOTA) token-based multi-instrument automatic music transcription (AMT) model. Despite SOTA performance, MT3 has the issue of instrument leakage, where transcriptions are fragmente
Externí odkaz:
http://arxiv.org/abs/2403.10024