Zobrazeno 1 - 10
of 13 274
pro vyhledávání: '"Shengyu An"'
Autor:
Liu, Yifei, Wen, Jicheng, Wang, Yang, Ye, Shengyu, Zhang, Li Lyna, Cao, Ting, Li, Cheng, Yang, Mao
Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits)
Externí odkaz:
http://arxiv.org/abs/2409.17066
Autor:
Zhong, Yinmin, Zhang, Zili, Wu, Bingyang, Liu, Shengyu, Chen, Yukun, Wan, Changyi, Hu, Hanpeng, Xia, Lei, Ming, Ranchen, Zhu, Yibo, Jin, Xin
Reinforcement Learning from Human Feedback (RLHF) enhances the alignment between LLMs and human preference. The workflow of RLHF typically involves several models and tasks in a series of distinct stages. Existing RLHF training systems view each task
Externí odkaz:
http://arxiv.org/abs/2409.13221
Visual-inertial systems have been widely studied and applied in the last two decades, mainly due to their low cost and power consumption, small footprint, and high availability. Such a trend simultaneously leads to a large amount of visual-inertial c
Externí odkaz:
http://arxiv.org/abs/2409.07116
With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning. However, existing research has primarily focused on text-based algebra problems, neglecting the study of geometry
Externí odkaz:
http://arxiv.org/abs/2409.09039
Autor:
Liu, Qichun, Lin, Jie, Wang, Xiaofeng, Dai, Zhibin, Sun, Yongkang, Xi, Gaobo, Mo, Jun, Liu, Jialian, Yan, Shengyu, Filippenko, Alexei V., Brink, Thomas G., Yang, Yi, Patra, Kishore C., Cai, Yongzhi, Chen, Zhihao, Chen, Liyang, Guo, Fangzhou, Jiang, Xiaojun, Li, Gaici, Li, Wenxiong, Lin, Weili, Miao, Cheng, Ma, Xiaoran, Peng, Haowei, Xia, Qiqi, Xiang, Danfeng, Zhang, Jicheng
The Tsinghua University--Ma Huateng Telescopes for Survey (TMTS) started to monitor the LAMOST plates in 2020, leading to the discovery of numerous short-period eclipsing binaries, peculiar pulsators, flare stars, and other variable objects. Here, we
Externí odkaz:
http://arxiv.org/abs/2408.12104
Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian Splats (3DGS) has recently shown promise towards more accurate, dense 3D scene maps. However, existing 3DGS-based methods fail to address the global consistency of the scene via loop c
Externí odkaz:
http://arxiv.org/abs/2408.10154
Aided inertial navigation system (INS), typically consisting of an inertial measurement unit (IMU) and an exteroceptive sensor, has been widely accepted as a feasible solution for navigation. Compared with vision-aided and LiDAR-aided INS, radar-aide
Externí odkaz:
http://arxiv.org/abs/2408.02444
In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrated by Large Language Models (LLMs
Externí odkaz:
http://arxiv.org/abs/2408.02103
Autor:
Lv, Zheqi, He, Shaoxuan, Zhan, Tianyu, Zhang, Shengyu, Zhang, Wenqiao, Chen, Jingyuan, Zhao, Zhou, Wu, Fei
Dynamic sequential recommendation (DSR) can generate model parameters based on user behavior to improve the personalization of sequential recommendation under various user preferences. However, it faces the challenges of large parameter search space
Externí odkaz:
http://arxiv.org/abs/2408.00123
The Minkowski problem in convex geometry concerns showing a given Borel measure on the unit sphere is, up to perhaps a constant, some type of surface area measure of a convex body. Two types of Minkowski problems in particular are an active area of r
Externí odkaz:
http://arxiv.org/abs/2407.20064