-
1تقرير
المؤلفون: Chen, Lina
مصطلحات موضوعية: Mathematics - Differential Geometry
الوصف: In this note, we will show that if a measured Gromov-Hausdorff limit space of a sequence of Riemannian manifolds with lower Ricci curvature bound has dense 2-regular set, then it is homeomorphic to a 2-dimensional manifold in an open full measure set. This result gives a positive answer to an open problem in [Naber, Open problem 3.4] in dimension 2 and for dimension larger than 2 there are counterexamples by [HNW, Zhou].
URL الوصول: http://arxiv.org/abs/2406.08306
-
2مؤتمر
المؤلفون: Chen, Lina, Zhang, Xin, Yao, Mingming
المصدر: 2023 4th International Conference on Power Engineering (ICPE) Power Engineering (ICPE), 2023 4th International Conference on. :323-328 Dec, 2023
Relation: 2023 4th International Conference on Power Engineering (ICPE)
-
3مؤتمر
المؤلفون: Meng, Liang, Zeng, Mingfei, Yang, Wenjie, Chen, Lina, Li, Siwei, Pan, Junbing
المصدر: 2023 International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE) Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE), 2023 International Conference on. :1-5 Nov, 2023
Relation: 2023 International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE)
-
4مؤتمر
المؤلفون: Chen, Lina, Wang, Jiamei, Wei, Ziliang, Pun, Sio Hang, Vai, Mang I., Gao, Yueming
المصدر: 2023 Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC) Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC), 2023. :1-3 Nov, 2023
Relation: 2023 Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC)
-
5مؤتمر
المؤلفون: Sun, Kai, Xiao, Xi, Wu, Shouzun, Chen, Lina
المصدر: 2023 11th International Conference on Power Electronics and ECCE Asia (ICPE 2023 - ECCE Asia) Power Electronics and ECCE Asia (ICPE 2023 - ECCE Asia), 2023 11th International Conference on. :440-445 May, 2023
Relation: 2023 11th International Conference on Power Electronics and ECCE Asia (ICPE 2023 - ECCE Asia)
-
6دورية أكاديمية
المؤلفون: Wu, JialinAff1, Aff2, Aff3, Aff4, Li, TingtingAff1, Aff2, Aff3, Xu, LinanAff1, Aff2, Aff3, Chen, LinaAff1, Aff2, Aff3, Liang, XiaoyanAff1, Aff2, Aff3, Lin, Aihua, Zhang, WangjianAff4, IDs10815024031532_cor7, Huang, RuiAff1, Aff2, Aff3, IDs10815024031532_cor8
المصدر: Journal of Assisted Reproduction and Genetics. :1-11
-
7دورية أكاديمية
المؤلفون: Liu, Pengqian, Xu, ChanghangAff1, IDs10973024132639_cor2, Zhang, Yubin, Chen, Lina, Liu, Rui, Wang, Longbo, Zhao, Qing
المصدر: Journal of Thermal Analysis and Calorimetry: An International Forum for Thermal Studies. :1-19
-
8مؤتمر
المؤلفون: Xie, Ming, Meng, Liang, Zeng, Mingfei, Chen, Lina, Li, Siwei
المصدر: 2023 International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) Distributed Computing and Electrical Circuits and Electronics (ICDCECE), 2023 International Conference on. :1-5 Apr, 2023
Relation: 2023 International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE)
-
9مؤتمر
المؤلفون: Meng, Liang, Zeng, Mingfei, Xie, Ming, Chen, Lina, Huang, Anni
المصدر: 2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT) Communication Systems and Network Technologies (CSNT), 2023 IEEE 12th International Conference on. :710-714 Apr, 2023
Relation: 2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)
-
10تقرير
المؤلفون: He, Qianyu, Zeng, Jie, Huang, Wenhao, Chen, Lina, Xiao, Jin, He, Qianxi, Zhou, Xunzhe, Chen, Lida, Wang, Xintao, Huang, Yuncheng, Ye, Haoning, Li, Zihan, Chen, Shisong, Zhang, Yikai, Gu, Zhouhong, Liang, Jiaqing, Xiao, Yanghua
مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence
الوصف: Large language models (LLMs) can understand human instructions, showing their potential for pragmatic applications beyond traditional NLP tasks. However, they still struggle with complex instructions, which can be either complex task descriptions that require multiple tasks and constraints, or complex input that contains long context, noise, heterogeneous information and multi-turn format. Due to these features, LLMs often ignore semantic constraints from task descriptions, generate incorrect formats, violate length or sample count constraints, and be unfaithful to the input text. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions, as they are close-ended and simple. To bridge this gap, we propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically. We design eight features for complex instructions and construct a comprehensive evaluation dataset from real-world scenarios. We also establish four criteria and develop corresponding metrics, as current ones are inadequate, biased or too strict and coarse-grained. We compare the performance of representative Chinese-oriented and English-oriented models in following complex instructions through extensive experiments. Resources of CELLO are publicly available at https://github.com/Abbey4799/CELLO.
URL الوصول: http://arxiv.org/abs/2309.09150