Zobrazeno 1 - 10
of 55 345
pro vyhledávání: '"Li, FENG"'
In the paradigm of decentralized learning, a group of agents collaborate to learn a global model using a distributed dataset without a central server; nevertheless, it is severely challenged by the heterogeneity of the data distribution across the ag
Externí odkaz:
http://arxiv.org/abs/2411.00365
Autor:
Jiang, Xun, Li, Feng, Zhao, Han, Wang, Jiaying, Shao, Jun, Xu, Shihao, Zhang, Shu, Chen, Weiling, Tang, Xavier, Chen, Yize, Wu, Mengyue, Ma, Weizhi, Wang, Mengdi, Chen, Tianqiao
Large language models (LLMs) like GPTs, trained on vast datasets, have demonstrated impressive capabilities in language understanding, reasoning, and planning, achieving human-level performance in various tasks. Most studies focus on enhancing these
Externí odkaz:
http://arxiv.org/abs/2410.15665
Autor:
Liu, Man, Bai, Huihui, Li, Feng, Zhang, Chunjie, Wei, Yunchao, Wang, Meng, Chua, Tat-Seng, Zhao, Yao
Generalized zero-shot learning (GZSL) endeavors to identify the unseen categories using knowledge from the seen domain, necessitating the intrinsic interactions between the visual features and attribute semantic features. However, GZSL suffers from i
Externí odkaz:
http://arxiv.org/abs/2410.11560
Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online sampling.
Externí odkaz:
http://arxiv.org/abs/2410.04834
Recent advances on time series forecasting mainly focus on improving the forecasting models themselves. However, managing the length of the input data can also significantly enhance prediction performance. In this paper, we introduce a novel approach
Externí odkaz:
http://arxiv.org/abs/2409.16843
Dynamic quantization has attracted rising attention in image super-resolution (SR) as it expands the potential of heavy SR models onto mobile devices while preserving competitive performance. Existing methods explore layer-to-bit configuration upon v
Externí odkaz:
http://arxiv.org/abs/2409.14330
Kernel smoothing is a widely used nonparametric method in modern statistical analysis. The problem of efficiently conducting kernel smoothing for a massive dataset on a distributed system is a problem of great importance. In this work, we find that t
Externí odkaz:
http://arxiv.org/abs/2409.14079
Publikováno v:
Physical Review Letters 133, 106101 (2024)
Topological surface states are unique to topological materials and are immune to disturbances. In isostatic lattices, mechanical topological floppy modes exhibit softness depending on the polarization relative to the terminating surface. However, in
Externí odkaz:
http://arxiv.org/abs/2409.02607
The last decade has witnessed a tremendous growth of service computing, while efficient service recommendation methods are desired to recommend high-quality services to users. It is well known that collaborative filtering is one of the most popular m
Externí odkaz:
http://arxiv.org/abs/2408.15688
Autor:
Zhang, Yi-Fan, Zhang, Huanyu, Tian, Haochen, Fu, Chaoyou, Zhang, Shuangqing, Wu, Junfei, Li, Feng, Wang, Kun, Wen, Qingsong, Zhang, Zhang, Wang, Liang, Jin, Rong, Tan, Tieniu
Comprehensive evaluation of Multimodal Large Language Models (MLLMs) has recently garnered widespread attention in the research community. However, we observe that existing benchmarks present several common barriers that make it difficult to measure
Externí odkaz:
http://arxiv.org/abs/2408.13257