Zobrazeno 1 - 10
of 14 947
pro vyhledávání: '"Xiao-Wen An"'
Autor:
Shao, Jie-Jing, Yang, Xiao-Wen, Zhang, Bo-Wen, Chen, Baizhi, Wei, Wen-Da, Cai, Guohao, Dong, Zhenhua, Guo, Lan-Zhe, Li, Yu-feng
Recent advances in LLMs, particularly in language reasoning and tool integration, have rapidly sparked the real-world development of Language Agents. Among these, travel planning represents a prominent domain, combining academic challenges with pract
Externí odkaz:
http://arxiv.org/abs/2412.13682
Autor:
Chen, Liang, Wang, Zekun, Ren, Shuhuai, Li, Lei, Zhao, Haozhe, Li, Yunshui, Cai, Zefan, Guo, Hongcheng, Zhang, Lei, Xiong, Yizhe, Zhang, Yichi, Wu, Ruoyu, Dong, Qingxiu, Zhang, Ge, Yang, Jian, Meng, Lingwei, Hu, Shujie, Chen, Yulong, Lin, Junyang, Bai, Shuai, Vlachos, Andreas, Tan, Xu, Zhang, Minjia, Xiao, Wen, Yee, Aaron, Liu, Tianyu, Chang, Baobao
Building on the foundations of language modeling in natural language processing, Next Token Prediction (NTP) has evolved into a versatile training objective for machine learning tasks across various modalities, achieving considerable success. As Larg
Externí odkaz:
http://arxiv.org/abs/2412.18619
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:
Ren, Yu-Meng, Pan, Xue-Feng, Yao, Xiao-Yu, Huo, Xiao-Wen, Zheng, Jun-Cong, Hei, Xin-Lei, Qiao, Yi-Fan, Li, Peng-Bo
Nonreciprocal interaction between two spatially separated subsystems plays a crucial role in signal processing and quantum networks. Here, we propose an efficient scheme to achieve nonreciprocal interaction and entanglement between two qubits by comb
Externí odkaz:
http://arxiv.org/abs/2411.06775
Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important for text gen
Externí odkaz:
http://arxiv.org/abs/2410.19258
Autor:
Cheng, Yi, Liang, Xiao, Gong, Yeyun, Xiao, Wen, Wang, Song, Zhang, Yuji, Hou, Wenjun, Xu, Kaishuai, Liu, Wenge, Li, Wenjie, Jiao, Jian, Chen, Qi, Cheng, Peng, Xiong, Wayne
Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models. Nonetheles
Externí odkaz:
http://arxiv.org/abs/2410.01556
Autor:
Shang, Xiao-Wen, Chen, Xuan, Hegade, Narendra N., Lan, Ze-Feng, Li, Xuan-Kun, Tang, Hao, Peng, Yu-Quan, Solano, Enrique, Jin, Xian-Min
Codesign, an integral part of computer architecture referring to the information interaction in hardware-software stack, is able to boost the algorithm mapping and execution in the computer hardware. This well applies to the noisy intermediate-scale
Externí odkaz:
http://arxiv.org/abs/2409.17930
In quantum mechanics, a long-standing question remains: How does a single photon traverse double slits? One intuitive picture suggests that the photon passes through only one slit, while its wavefunction splits into an ``empty" wave and a ``full" wav
Externí odkaz:
http://arxiv.org/abs/2409.13383
The ability of Graph Neural Networks (GNNs) to capture long-range and global topology information is limited by the scope of conventional graph Laplacian, leading to unsatisfactory performance on some datasets, particularly on heterophilic graphs. To
Externí odkaz:
http://arxiv.org/abs/2409.09888
Autor:
Luan, Sitao, Lu, Qincheng, Hua, Chenqing, Wang, Xinyu, Zhu, Jiaqi, Chang, Xiao-Wen, Wolf, Guy, Tang, Jian
Over the past decade, Graph Neural Networks (GNNs) have achieved great success on machine learning tasks with relational data. However, recent studies have found that heterophily can cause significant performance degradation of GNNs, especially on no
Externí odkaz:
http://arxiv.org/abs/2409.05755