Zobrazeno 1 - 10
of 7 805
pro vyhledávání: '"He, Liang"'
Preference-Based reinforcement learning (PBRL) learns directly from the preferences of human teachers regarding agent behaviors without needing meticulously designed reward functions. However, existing PBRL methods often learn primarily from explicit
Externí odkaz:
http://arxiv.org/abs/2409.07268
Tikhonov regularized inertial primal-dual dynamics for convex-concave bilinear saddle point problems
In this paper, for a convex-concave bilinear saddle point problem, we propose a Tikhonov regularized second-order primal-dual dynamical system with slow damping, extrapolation and general time scaling parameters. Depending on the vanishing speed of t
Externí odkaz:
http://arxiv.org/abs/2409.05301
Autor:
Liu, Wentao, Pan, Qianjun, Zhang, Yi, Liu, Zhuo, Wu, Ji, Zhou, Jie, Zhou, Aimin, Chen, Qin, Jiang, Bo, He, Liang
Large language models (LLMs) have obtained promising results in mathematical reasoning, which is a foundational skill for human intelligence. Most previous studies focus on improving and measuring the performance of LLMs based on textual math reasoni
Externí odkaz:
http://arxiv.org/abs/2409.02834
Publikováno v:
2024 IEEE International Conference on Multimedia and Expo (ICME 2024)
Although current text-guided music generation technology can cope with simple creative scenarios, achieving fine-grained control over individual text-modality conditions remains challenging as user demands become more intricate. Accordingly, we intro
Externí odkaz:
http://arxiv.org/abs/2408.04865
Non-Hermitian systems can manifest rich static and dynamical properties at their exceptional points (EPs). Here, we identify yet another class of distinct phenomena that is hinged on EPs, namely, the emergence of a series of non-Hermitian conservatio
Externí odkaz:
http://arxiv.org/abs/2408.01092
Autor:
Yang, Xuemeng, Wen, Licheng, Ma, Yukai, Mei, Jianbiao, Li, Xin, Wei, Tiantian, Lei, Wenjie, Fu, Daocheng, Cai, Pinlong, Dou, Min, Shi, Botian, He, Liang, Liu, Yong, Qiao, Yu
This paper presented DriveArena, the first high-fidelity closed-loop simulation system designed for driving agents navigating in real scenarios. DriveArena features a flexible, modular architecture, allowing for the seamless interchange of its core c
Externí odkaz:
http://arxiv.org/abs/2408.00415
With the introduction of large language models (LLMs), automatic math reasoning has seen tremendous success. However, current methods primarily focus on providing solutions or using techniques like Chain-of-Thought to enhance problem-solving accuracy
Externí odkaz:
http://arxiv.org/abs/2407.17349
Autor:
Chen, Wenjie, Yang, Qi, Liu, Qi, Zhang, Yiqun, He, Liang, Xia, Yuanlin, Wang, Zhuqing, Huang, Yubo, Chen, Jianfeng, Xia, Cao
For traditional capacitive pressure sensors, high nonlinearity and poor sensitivity greatly limited their sensing applications. Hence, an innovative design of capacitors based on spiral comb electrodes is proposed for high-sensitivity pressure detect
Externí odkaz:
http://arxiv.org/abs/2407.08559
Autor:
Zhang, Zhe, Li, Zhuoyi, Chen, Yuzhe, Zhu, Fangyuan, Yan, Yu, Li, Yao, He, Liang, Du, Jun, Zhang, Rong, Wu, Jing, Lu, Xianyang, Xu, Yongbing
Realizing deterministic current-induced spin-orbit torque (SOT) magnetization switching, especially in systems exhibiting perpendicular magnetic anisotropy (PMA), typically requires the application of a collinear in-plane field, posing a challenging
Externí odkaz:
http://arxiv.org/abs/2407.03676
We introduce JuliVQC: a light-weight, yet extremely efficient variational quantum circuit simulator. JuliVQC is part of an effort for classical simulation of the \textit{Zuchongzhi} quantum processors, where it is extensively used to characterize the
Externí odkaz:
http://arxiv.org/abs/2406.19212