Energy
COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation
Our insight is that satellite's earth observation photos are not just images
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
Then we propose a platform, coined Geom3D, which enables benchmarking the effectiveness of geometric strategies.
5,000-year-old bacteria thawed in Romanian ice cave
Breakthroughs, discoveries, and DIY tips sent six days a week. Whether it's the ocean's deepest hydrothermal vents or tall mountain peaks, bacteria is likely surviving and thriving. Ice caves can host a wide variety of microorganisms and offer biologists a bevy of genetic diversity that still has to be studied. And it could help save lives. A team of scientists in Romania tested antibiotic resistance profiles with a bacterial strain that was hidden in a 5,000-year-old layer of ice inside an underground ice cave.
Infusing Self-Consistency into Density Functional Theory Hamiltonian Prediction via Deep Equilibrium Models
We propose a versatile framework that combines DEQ with off-the-shelf machine learning models for predicting Hamiltonians.
Energy Consumption Analysis Details
The spike firing rate is defined as the proportion of non-zero elements in the spike tensor. In Table S1, we present the spike firing rates for all spiking tensors in spike-driven Transformer-8-512. SNNs are theoretically more energy efficient than counterpart ANNs. We employ two types of datasets: static image classification and neuromorphic classification. ImageNet-1K is the most typical static image dataset, which is widely used in the field of image classification.
DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching
In this paper, we intent to handle this emerging issue.
Disentangling Linear Quadratic Control with Untrusted ML Predictions Tongxin Li1 Hao Liu
We study the problem of online decision-making with predictions.
