Zobrazeno 1 - 10
of 5 848
pro vyhledávání: '"Sun, Hai"'
Quantum metric, a probe to spacetime of the Hilbert space, has been found measurable in the nonlinear electronic transport and attracted tremendous interest. We show that the quantum metric is only a tip of the iceberg, by deriving unknown 11 out of
Externí odkaz:
http://arxiv.org/abs/2410.04995
We study the influence of external electric and Zeeman fields on the Josephson response in a planar superconductor/altermagnet/superconductor junction. Remarkably, we discover that the current-phase relation can be forward- or backward-skewed due to
Externí odkaz:
http://arxiv.org/abs/2407.19413
We present a deep neural network-enabled method to accelerate near-field (NF) antenna measurement. We develop a Near-field Super-resolution Network (NFS-Net) to reconstruct significantly undersampled near-field data as high-resolution data, which con
Externí odkaz:
http://arxiv.org/abs/2406.17244
Autor:
Sun, Hai-Long, Zhou, Da-Wei, Li, Yang, Lu, Shiyin, Yi, Chao, Chen, Qing-Guo, Xu, Zhao, Luo, Weihua, Zhang, Kaifu, Zhan, De-Chuan, Ye, Han-Jia
The rapid development of Multimodal Large Language Models (MLLMs) like GPT-4V has marked a significant step towards artificial general intelligence. Existing methods mainly focus on aligning vision encoders with LLMs through supervised fine-tuning (S
Externí odkaz:
http://arxiv.org/abs/2406.02539
Autor:
Huang, Kaichen, Shao, Minghao, Wan, Shenghua, Sun, Hai-Hang, Feng, Shuai, Gan, Le, Zhan, De-Chuan
In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation. Previous methods have generally solved this problem by domain alignm
Externí odkaz:
http://arxiv.org/abs/2404.03386
Autor:
Huang, Kaichen, Sun, Hai-Hang, Wan, Shenghua, Shao, Minghao, Feng, Shuai, Gan, Le, Zhan, De-Chuan
Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications. In this work, we focus on the problem of Learning from Noisy Demonstrations (LND), where the imita
Externí odkaz:
http://arxiv.org/abs/2404.03382
Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often results in the
Externí odkaz:
http://arxiv.org/abs/2403.12030
Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of former kn
Externí odkaz:
http://arxiv.org/abs/2401.16386
Autor:
Sun, Tao, Sun, Hai-Wei
In this paper, we investigate the numerical solution of the two-dimensional fractional Laplacian wave equations. After splitting out the Riesz fractional derivatives from the fractional Laplacian, we treat the Riesz fractional derivatives with an imp
Externí odkaz:
http://arxiv.org/abs/2312.06206
While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data. As a solution, incremental learning emerges to addre
Externí odkaz:
http://arxiv.org/abs/2309.07117