Zobrazeno 1 - 10
of 3 557
pro vyhledávání: '"Zhi, Qin"'
Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise, especially in crowdsourcing scenarios. Most prior object detection methods assume accurate annotations; A few recent works h
Externí odkaz:
http://arxiv.org/abs/2407.07958
Autor:
Si, Dawei, Xiao, Sheng, Qin, Yuhao, Wang, Yijie, Xu, Junhuai, Tian, Baiting, Zhang, Boyuan, Guo, Dong, Zhi, Qin, Wei, Xiaobao, Hao, Yibo, Wang, Zengxiang, Zhuo, Tianren, Yang, Yuansheng, Wei, Xianglun, Yang, Herun, Ma, Peng, Duan, Limin, Duan, Fangfang, Ma, Junbing, Xu, Shiwei, Bai, Zhen, Yang, Guo, Yang, Yanyun, Xiao, Zhigang
The emission of neutrons from heavy ion reactions is an important observable for studying the asymmetric nuclear equation of state and the reaction dynamics. A 20-unit neutron array has been developed and mounted on the compact spectrometer for heavy
Externí odkaz:
http://arxiv.org/abs/2406.18605
Grokking is the phenomenon where neural networks NNs initially fit the training data and later generalize to the test data during training. In this paper, we empirically provide a frequency perspective to explain the emergence of this phenomenon in N
Externí odkaz:
http://arxiv.org/abs/2405.17479
Autor:
Wang, Zhiwei, Wang, Yunji, Zhang, Zhongwang, Zhou, Zhangchen, Jin, Hui, Hu, Tianyang, Sun, Jiacheng, Li, Zhenguo, Zhang, Yaoyu, Xu, Zhi-Qin John
Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training strategie
Externí odkaz:
http://arxiv.org/abs/2405.15302
Transformers have shown impressive capabilities across various tasks, but their performance on compositional problems remains a topic of debate. In this work, we investigate the mechanisms of how transformers behave on unseen compositional tasks. We
Externí odkaz:
http://arxiv.org/abs/2405.05409
Using neural networks to solve partial differential equations (PDEs) is gaining popularity as an alternative approach in the scientific computing community. Neural networks can integrate different types of information into the loss function. These in
Externí odkaz:
http://arxiv.org/abs/2405.03095
Autor:
Chen, Tianyi, Xu, Zhi-Qin John
Neural networks have been extensively applied to a variety of tasks, achieving astounding results. Applying neural networks in the scientific field is an important research direction that is gaining increasing attention. In scientific applications, t
Externí odkaz:
http://arxiv.org/abs/2405.01041
We present a novel yet simple deep learning approach, called input gradient annealing neural network (IGANN), for solving stationary Fokker-Planck equations. Traditional methods, such as finite difference and finite elements, suffer from the curse of
Externí odkaz:
http://arxiv.org/abs/2405.00317
Autor:
Lin, Che-Tsung, Ng, Chun Chet, Tan, Zhi Qin, Nah, Wan Jun, Wang, Xinyu, Kew, Jie Long, Hsu, Pohao, Lai, Shang Hong, Chan, Chee Seng, Zach, Christopher
Extremely low-light text images are common in natural scenes, making scene text detection and recognition challenging. One solution is to enhance these images using low-light image enhancement methods before text extraction. However, previous methods
Externí odkaz:
http://arxiv.org/abs/2404.14135
For a long time, research on time series anomaly detection has mainly focused on finding outliers within a given time series. Admittedly, this is consistent with some practical problems, but in other practical application scenarios, people are concer
Externí odkaz:
http://arxiv.org/abs/2402.02007