Tech Times

Compile Once, Run Offline: New AI Method Matches 32B Models With a 23MB File

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...

Physicists and AI model Claude 'collaborate' to prove a 10-year-old jamming conjecture

A mathematical problem that had remained unsolved for more than 10 years in the physics of complex systems has finally been ...
IEEE

Blind Recovery of Sparse Signals From Subsampled Convolution

Abstract: Subsampled blind deconvolution is the recovery of two unknown signals from samples of their convolution. To overcome the ill-posedness of this problem, solutions based on priors tailored to ...
IEEE

LWCDNet: A Lightweight Fully Convolution Network for Change Detection in Optical Remote Sensing Imagery

Abstract: Change detection (CD) is an important task in remote sensing image processing. The main research goal is to identify whether the target area has changed. Recently, the rise of deep learning ...
PNAS

Convolution identities for divisor sums and modular forms

Our research proves a conjecture from string theory asserting the vanishing of a specific convolution sum arising in the 4-graviton scattering amplitude in 10-dimensional type IIB string theory. The ...
Frontiers

Detection Method of Citrus Psyllids With Field High-Definition Camera Based on Improved Cascade Region-Based Convolution Neural Networks

Citrus psyllid is the only insect vector of citrus Huanglongbing (HLB), which is the most destructive disease in the citrus industry. There is no effective treatment for HLB, so detecting citrus ...
Frontiers

Motor Imagery EEG Signal Recognition Using Deep Convolution Neural Network

Brain computer interaction (BCI) based on EEG can help patients with limb dyskinesia to carry out daily life and rehabilitation training. However, due to the low signal-to-noise ratio and large ...