Zobrazeno 1 - 10
of 57 732
pro vyhledávání: '"AN Wenlong"'
Dynamic scheduling of access to shared resources by autonomous systems is a challenging problem, characterized as being NP-hard. The complexity of this task leads to a combinatorial explosion of possibilities in highly dynamic systems where arriving
Externí odkaz:
http://arxiv.org/abs/2410.18786
Autor:
Shi, Guangyuan, Lu, Zexin, Dong, Xiaoyu, Zhang, Wenlong, Zhang, Xuanyu, Feng, Yujie, Wu, Xiao-Ming
Aligning large language models (LLMs) through fine-tuning is essential for tailoring them to specific applications. Therefore, understanding what LLMs learn during the alignment process is crucial. Recent studies suggest that alignment primarily adju
Externí odkaz:
http://arxiv.org/abs/2410.17875
In this work, we investigate the inverse problem of recovering a potential in an elliptic problem from random pointwise observations in the domain. We employ a regularized output-least squares formulation with an $H^1(\Omega)$ penalty for the numeric
Externí odkaz:
http://arxiv.org/abs/2410.14106
Autor:
Cai, Wenlong, Chen, Zanhong, Shi, Yuzhang, Zhu, Daoqian, Yang, Guang, Du, Ao, Lu, Shiyang, Cao, Kaihua, Liu, Hongxi, Shi, Kewen, Zhao, Weisheng
Current-induced antiferromagnetic (AFM) switching remains critical in spintronics, yet the interplay between thermal effects and spin torques still lacks clear clarification. Here we experimentally investigate the thermally interplayed spin-orbit tor
Externí odkaz:
http://arxiv.org/abs/2410.13202
Autor:
Deng, Wenlong, Zhao, Yize, Vakilian, Vala, Chen, Minghui, Li, Xiaoxiao, Thrampoulidis, Christos
Storing open-source fine-tuned models separately introduces redundancy and increases response times in applications utilizing multiple models. Delta-parameter pruning (DPP), particularly the random drop and rescale (DARE) method proposed by Yu et al.
Externí odkaz:
http://arxiv.org/abs/2410.09344
Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often demands complex and deep architectures, which are expensive to compute and tra
Externí odkaz:
http://arxiv.org/abs/2410.08893
Detecting Out-of-Distribution (OOD) inputs is crucial for improving the reliability of deep neural networks in the real-world deployment. In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method th
Externí odkaz:
http://arxiv.org/abs/2410.07617
Autor:
Fu, Lirong, Liu, Peiyu, Meng, Wenlong, Lu, Kangjie, Zhou, Shize, Zhang, Xuhong, Chen, Wenzhi, Ji, Shouling
AI-powered binary code similarity detection (BinSD), which transforms intricate binary code comparison to the distance measure of code embedding through neural networks, has been widely applied to program analysis. However, due to the diversity of th
Externí odkaz:
http://arxiv.org/abs/2410.07537
Autor:
Gong, Junchao, Tu, Siwei, Yang, Weidong, Fei, Ben, Chen, Kun, Zhang, Wenlong, Yang, Xiaokang, Ouyang, Wanli, Bai, Lei
Precipitation nowcasting plays a pivotal role in socioeconomic sectors, especially in severe convective weather warnings. Although notable progress has been achieved by approaches mining the spatiotemporal correlations with deep learning, these metho
Externí odkaz:
http://arxiv.org/abs/2410.05805
Despite significant advancements, Large Language Models (LLMs) exhibit blind spots that impair their ability to retrieve and process relevant contextual data effectively. We demonstrate that LLM performance in graph tasks with complexities beyond the
Externí odkaz:
http://arxiv.org/abs/2410.01985