Zobrazeno 1 - 10
of 211
pro vyhledávání: '"Liang Siqi"'
Advancements in large language models (LLMs) have shown their effectiveness in multiple complicated natural language reasoning tasks. A key challenge remains in adapting these models efficiently to new or unfamiliar tasks. In-context learning (ICL) p
Externí odkaz:
http://arxiv.org/abs/2408.00144
Independent and identically distributed (i.i.d.) data is essential to many data analysis and modeling techniques. In the medical domain, collecting data from multiple sites or institutions is a common strategy that guarantees sufficient clinical dive
Externí odkaz:
http://arxiv.org/abs/2405.15081
Publikováno v:
Cybernetics and Information Technologies, Vol 16, Iss 6, Pp 60-68 (2016)
An ECG baseline shift correction method is presented on the base of the adaptive bionic wavelet transform. After modifying the bionic wavelet transform according to the characteristics of the ECG signal, we propose a novel adaptive BWT algorithm. Usi
Externí odkaz:
https://doaj.org/article/0fc7428dfcd44ef78259452d4473724f
Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients. But meanwhile, the distributed and isolated nature of data isolation may be complicated by data quality, making it more vulnerable to n
Externí odkaz:
http://arxiv.org/abs/2306.11650
Autonomous exploration is a crucial aspect of robotics that has numerous applications. Most of the existing methods greedily choose goals that maximize immediate reward. This strategy is computationally efficient but insufficient for overall explorat
Externí odkaz:
http://arxiv.org/abs/2304.00852
Recent advances in LiDAR technology have opened up new possibilities for robotic navigation. Given the widespread use of occupancy grid maps (OGMs) in robotic motion planning, this paper aims to address the challenges of integrating LiDAR with OGMs.
Externí odkaz:
http://arxiv.org/abs/2302.14819
Autor:
Liang, Siqi, Liang, Faming
Publikováno v:
Statistics and Its Interface 2023
Graphical models have long been studied in statistics as a tool for inferring conditional independence relationships among a large set of random variables. The most existing works in graphical modeling focus on the cases that the data are Gaussian or
Externí odkaz:
http://arxiv.org/abs/2212.04585
Sufficient dimension reduction is a powerful tool to extract core information hidden in the high-dimensional data and has potentially many important applications in machine learning tasks. However, the existing nonlinear sufficient dimension reductio
Externí odkaz:
http://arxiv.org/abs/2210.04349
In this paper, we address the problem of online quadrotor whole-body motion planning (SE(3) planning) in unknown and unstructured environments. We propose a novel multi-resolution search method, which discovers narrow areas requiring full pose planni
Externí odkaz:
http://arxiv.org/abs/2209.06761
Autor:
Zhu, Fangcheng, Ren, Yunfan, Kong, Fanze, Wu, Huajie, Liang, Siqi, Chen, Nan, Xu, Wei, Zhang, Fu
Accurate self and relative state estimation are the critical preconditions for completing swarm tasks, e.g., collaborative autonomous exploration, target tracking, search and rescue. This paper proposes Swarm-LIO: a fully decentralized state estimati
Externí odkaz:
http://arxiv.org/abs/2209.06628