Zobrazeno 1 - 10
of 190
pro vyhledávání: '"WANG Mingze"'
Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of surface changes between multi-temporal remote sensing images, detailing the categories, locations, and dynamics of changed objects (e.g., additions or di
Externí odkaz:
http://arxiv.org/abs/2411.11360
Transformers have demonstrated exceptional in-context learning capabilities, yet the theoretical understanding of the underlying mechanisms remain limited. A recent work (Elhage et al., 2021) identified a "rich" in-context mechanism known as inductio
Externí odkaz:
http://arxiv.org/abs/2410.11474
Sharpness-Aware Minimization (SAM) has substantially improved the generalization of neural networks under various settings. Despite the success, its effectiveness remains poorly understood. In this work, we discover an intriguing phenomenon in the tr
Externí odkaz:
http://arxiv.org/abs/2410.10373
Recommender systems have achieved increasing accuracy over the years. However, this precision often leads users to narrow their interests, resulting in issues such as limited diversity and the creation of echo chambers. Current research addresses the
Externí odkaz:
http://arxiv.org/abs/2409.04827
Autor:
Li, Pan, Li, Linfeng, Wang, Mingze, Cao, KaiMing, Gao, Ruihong, Liu, Heshan, Shi, Meng, Luo, Ziren
This paper reports the achievement of 120W single-frequency narrow linewidth 1018nm laser based on wide-tunable DBR fiber seed source. The DBR structure seed source uses 8mm long doped optical fibers with a line width of 3.25k. The wavelength tuning
Externí odkaz:
http://arxiv.org/abs/2407.19641
The widespread use of large language models (LLMs) has sparked concerns about the potential misuse of AI-generated text, as these models can produce content that closely resembles human-generated text. Current detectors for AI-generated text (AIGT) l
Externí odkaz:
http://arxiv.org/abs/2406.01179
Autor:
Wang, Mingze, Wang, Jinbo, He, Haotian, Wang, Zilin, Huang, Guanhua, Xiong, Feiyu, Li, Zhiyu, E, Weinan, Wu, Lei
In this work, we propose an Implicit Regularization Enhancement (IRE) framework to accelerate the discovery of flat solutions in deep learning, thereby improving generalization and convergence. Specifically, IRE decouples the dynamics of flat and sha
Externí odkaz:
http://arxiv.org/abs/2405.20763
Autor:
Wang, Mingze, Su, Lili, Yan, Cilin, Xu, Sheng, Yuan, Pengcheng, Jiang, Xiaolong, Zhang, Baochang
The intelligent interpretation of buildings plays a significant role in urban planning and management, macroeconomic analysis, population dynamics, etc. Remote sensing image building interpretation primarily encompasses building extraction and change
Externí odkaz:
http://arxiv.org/abs/2403.07564
Symmetries are prevalent in deep learning and can significantly influence the learning dynamics of neural networks. In this paper, we examine how exponential symmetries -- a broad subclass of continuous symmetries present in the model architecture or
Externí odkaz:
http://arxiv.org/abs/2402.07193
Autor:
Wang, Mingze, E, Weinan
We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the dot-product self
Externí odkaz:
http://arxiv.org/abs/2402.00522