Zobrazeno 1 - 10
of 12 836
pro vyhledávání: '"Bo-Wen An"'
While scaling laws optimize training configurations for large language models (LLMs) through experiments on smaller or early-stage models, they fail to predict emergent abilities due to the absence of such capabilities in these models. To address thi
Externí odkaz:
http://arxiv.org/abs/2412.07111
Autor:
Zhang, Bo-Wen, Qiu, Xi-Yang, Ma, Yicheng, Hu, Qingmei, Fitó-Parera, Aina, Kohata, Ikuma, Feng, Ya, Zheng, Yongjia, Zhang, Chiyu, Matsuo, Yutaka, Wang, YuHuang, Chiashi, Shohei, Otsuka, Keigo, Xiang, Rong, Levshov, Dmitry I., Cambré, Sofie, Wenseleers, Wim, Rotkin, Slava V., Maruyama, Shigeo
Carbyne, a one-dimensional (1D) carbon allotrope with alternating triple and single bonds, has the highest known mechanical strength but is unstable to bending, limiting synthesis to short linear chains. Encapsulation within carbon nanotubes (CNTs) s
Externí odkaz:
http://arxiv.org/abs/2411.18899
Autor:
Yu, Bo-Wen, Liu, Bang-Gui
We investigate through first-principles calculations rutile CoF$_2$ as an altermagnetic material. It is confirmed that there are two antiparallel magnetic moments of Co ions in the unit cell and the magnetic easy axis is in the z axis. A giant nonrel
Externí odkaz:
http://arxiv.org/abs/2411.16188
Vision representation learning, especially self-supervised learning, is pivotal for various vision applications. Ensemble learning has also succeeded in enhancing the performance and robustness of the vision models. However, traditional ensemble stra
Externí odkaz:
http://arxiv.org/abs/2411.15787
Autor:
Han, Xiao-Qi, Wang, Xin-De, Xu, Meng-Yuan, Feng, Zhen, Yao, Bo-Wen, Guo, Peng-Jie, Gao, Ze-Feng, Lu, Zhong-Yi
The discovery of advanced materials is the cornerstone of human technological development and progress. The structures of materials and their corresponding properties are essentially the result of a complex interplay of multiple degrees of freedom su
Externí odkaz:
http://arxiv.org/abs/2411.09429
Autor:
Gu, Shuhao, Zhang, Jialing, Zhou, Siyuan, Yu, Kevin, Xing, Zhaohu, Wang, Liangdong, Cao, Zhou, Jia, Jintao, Zhang, Zhuoyi, Wang, Yixuan, Hu, Zhenchong, Zhang, Bo-Wen, Li, Jijie, Liang, Dong, Zhao, Yingli, Ao, Yulong, Liu, Yaoqi, Feng, Fangxiang, Liu, Guang
Vision-Language Models (VLMs) have recently made significant progress, but the limited scale and quality of open-source instruction data hinder their performance compared to closed-source models. In this work, we address this limitation by introducin
Externí odkaz:
http://arxiv.org/abs/2410.18558
Autor:
Wang, Liangdong, Zhang, Bo-Wen, Wu, Chengwei, Zhao, Hanyu, Shi, Xiaofeng, Gu, Shuhao, Li, Jijie, Ma, Quanyue, Pan, TengFei, Liu, Guang
We present CCI3.0-HQ (https://huggingface.co/datasets/BAAI/CCI3-HQ), a high-quality 500GB subset of the Chinese Corpora Internet 3.0 (CCI3.0)(https://huggingface.co/datasets/BAAI/CCI3-Data), developed using a novel two-stage hybrid filtering pipeline
Externí odkaz:
http://arxiv.org/abs/2410.18505
Autor:
Yu, Bo-Wen, Liu, Bang-Gui
It is highly desirable to modify and improve the Dirac electron system of graphene for novel electronic properties and promising applications. For this purpose, we study 2D heterostructures consisting of graphene and monolayer TMDs by means of first-
Externí odkaz:
http://arxiv.org/abs/2410.02542
Autor:
Zhang, Bo-Wen, Wang, Liangdong, Li, Jijie, Gu, Shuhao, Wu, Xinya, Zhang, Zhengduo, Gao, Boyan, Ao, Yulong, Liu, Guang
This paper introduces the Aquila2 series, which comprises a wide range of bilingual models with parameter sizes of 7, 34, and 70 billion. These models are trained based on an innovative framework named HeuriMentor (HM), which offers real-time insight
Externí odkaz:
http://arxiv.org/abs/2408.07410
Autor:
Zhang, Bo-Wen, Wang, Liangdong, Yuan, Ye, Li, Jijie, Gu, Shuhao, Zhao, Mengdi, Wu, Xinya, Liu, Guang, Wu, Chengwei, Zhao, Hanyu, Du, Li, Ju, Yiming, Ma, Quanyue, Ao, Yulong, Zhao, Yingli, Zhu, Songhe, Cao, Zhou, Liang, Dong, Lin, Yonghua, Zhang, Ming, Wang, Shunfei, Zhou, Yanxin, Ye, Min, Chen, Xuekai, Yu, Xinyang, Huang, Xiangjun, Yang, Jian
In recent years, with the rapid application of large language models across various fields, the scale of these models has gradually increased, and the resources required for their pre-training have grown exponentially. Training an LLM from scratch wi
Externí odkaz:
http://arxiv.org/abs/2408.06567