Search papers, labs, and topics across Lattice.
Hunan University
7
0
6
MSBraM achieves unprecedented performance in EEG analysis by mastering the complex interplay of local and global neural dynamics.
Riemannian self-attention can revolutionize EEG decoding by overcoming the limitations of traditional metrics, leading to more accurate brain-computer interfaces.
CERS leverages Chain-of-Thought reasoning to enhance medical image segmentation, significantly improving accuracy in clinically challenging scenarios where visual cues alone fall short.
RepNet outperforms traditional DNNs in modeling high-frequency functions while maintaining computational efficiency.
Synthesizing FFA from non-invasive CFP using OCT guidance not only improves image quality but also boosts diagnostic accuracy for retinal diseases.
Transitioning from Dirac mass initial conditions, this framework achieves robust approximations of Fokker-Planck solutions, even in the face of numerical instabilities.
Forget Kalman filters: AFSF leverages conditional normalizing flows to amortize Bayesian filtering and smoothing in high-dimensional nonlinear systems, enabling accurate trajectory estimation and extrapolation.
