Zobrazeno 1 - 10
of 212
pro vyhledávání: '"Liu Zichuan"'
Autor:
Wang, Tianchun, Chen, Yuanzhou, Liu, Zichuan, Chen, Zhanwen, Chen, Haifeng, Zhang, Xiang, Cheng, Wei
The advent of large language models (LLMs) has revolutionized the field of text generation, producing outputs that closely mimic human-like writing. Although academic and industrial institutions have developed detectors to prevent the malicious usage
Externí odkaz:
http://arxiv.org/abs/2410.19230
Autor:
Wu, Mingyuan, Liu, Zichuan, Zheng, Haozhen, Guo, Hongpeng, Chen, Bo, Lu, Xin, Nahrstedt, Klara
Efficient single instance segmentation is essential for unlocking features in the mobile imaging applications, such as capture or editing. Existing on-the-fly mobile imaging applications scope the segmentation task to portraits or the salient subject
Externí odkaz:
http://arxiv.org/abs/2406.14874
Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models generate heatmaps, indicating the probability distribution of each edg
Externí odkaz:
http://arxiv.org/abs/2406.03503
Autor:
Liu, Zhihao, Yang, Xianliang, Liu, Zichuan, Xia, Yifan, Jiang, Wei, Zhang, Yuanyu, Li, Lijuan, Fan, Guoliang, Song, Lei, Jiang, Bian
Multi-agent reinforcement learning (MARL) is employed to develop autonomous agents that can learn to adopt cooperative or competitive strategies within complex environments. However, the linear increase in the number of agents leads to a combinatoria
Externí odkaz:
http://arxiv.org/abs/2405.16854
Autor:
Liu, Zichuan, Wang, Tianchun, Shi, Jimeng, Zheng, Xu, Chen, Zhuomin, Song, Lei, Dong, Wenqian, Obeysekera, Jayantha, Shirani, Farhad, Luo, Dongsheng
Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information
Externí odkaz:
http://arxiv.org/abs/2405.09308
Autor:
Liu, Zichuan, Wang, Zefan, Xu, Linjie, Wang, Jinyu, Song, Lei, Wang, Tianchun, Chen, Chunlin, Cheng, Wei, Bian, Jiang
The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to ethically align LLMs, these are often fragile and can be circumvented by
Externí odkaz:
http://arxiv.org/abs/2404.13968
Autor:
Xu, Linjie, Liu, Zichuan, Dockhorn, Alexander, Perez-Liebana, Diego, Wang, Jinyu, Song, Lei, Bian, Jiang
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial observability,
Externí odkaz:
http://arxiv.org/abs/2404.09715
Autor:
Liu, Zichuan, Zhang, Yingying, Wang, Tianchun, Wang, Zefan, Luo, Dongsheng, Du, Mengnan, Wu, Min, Wang, Yi, Chen, Chunlin, Fan, Lunting, Wen, Qingsong
Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns. Although previous saliency-based methods addressed the challenges, their perturbati
Externí odkaz:
http://arxiv.org/abs/2401.08552
Autor:
Wang, Zefan, Liu, Zichuan, Zhang, Yingying, Zhong, Aoxiao, Wang, Jihong, Yin, Fengbin, Fan, Lunting, Wu, Lingfei, Wen, Qingsong
Large language model (LLM) applications in cloud root cause analysis (RCA) have been actively explored recently. However, current methods are still reliant on manual workflow settings and do not unleash LLMs' decision-making and environment interacti
Externí odkaz:
http://arxiv.org/abs/2310.16340
In cooperative multi-agent reinforcement learning (MARL), the environmental stochasticity and uncertainties will increase exponentially when the number of agents increases, which puts hard pressure on how to come up with a compact latent representati
Externí odkaz:
http://arxiv.org/abs/2305.07182