Scientific Research Publishing

Machine Learning for Financial Risk Management: Modeling Time-Varying Factor Sensitivities Using Factor Variational Autoencoders ()

Accurate measurement of time-varying systematic risk exposures is essential for robust financial risk management.
Network World

Alibaba is developing an AI inference chip amid US export curbs

The new 7nm-class chip, reportedly in testing, signals a shift to domestic fabrication and aims to rival Nvidia’s China-compliant GPUs while maintaining CUDA compatibility. Alibaba is reportedly ...
Science Daily

AI just found 5 powerful materials that could replace lithium batteries

AI is helping scientists crack the code on next-gen batteries that could replace lithium-ion tech. By discovering novel porous materials, researchers may have paved the way for more powerful and ...
IEEE

Autoencoder-Based Transceivers for Multiple Access Human Body Communication Networks

Abstract: The Internet of Bodies (IoB) represents a transformative technological innovation that merges the bio-physical and digital realms through networks of intelligent devices positioned in, on, ...
GitHub

Random Segmentation fault in test_masked_autoencoder_vit

[2025-06-17T20:37:02.135Z] Starting test: test_access_attn_matrix (tests.test_masked_autoencoder_vit.TestMaskedAutoencoderViT)... [2025-06-17T20:37:02.135Z] 2025-06 ...
GitHub

TorchScript based ONNX exporter: Shape Inference failure

I want to export the AutoencoderKLCosmos model to ONNX using the TorchScript-based exporter. I'm using the script below import torch from diffusers.models import AutoencoderKLCosmos dtype = ...
IEEE

Deep Learning-Based Coseismic Deformation Estimation From InSAR Interferograms

Abstract: Accurate automated extraction of coseismic deformation from synthetic aperture radar (SAR) data can be challenging owing to interference from inherent atmospheric noise. Particularly, the ...