College of Computing - Georgia Tech

Ph.D. Student’s Framework Used to Bolster Nvidia’s Cosmos Predict-2 Model

Nvidia used NATTEN to fine-tune its prediction model, Cosmos Predict, and the company introduced the second version of the ...

Why we see things in the dark: How our brains work in absence of light

Our brains actively construct vision in near-darkness, blending residual light with memory and prediction. Even with minimal ...

Cursor introduces its coding model alongside multi-agent interface

To address that, Cursor introduced Composer alongside its new multi-agent interface, which allows you to “run many agents in ...
IEEE

Leveraging Convolutional Neural Network-Transformer Synergy for Predictive Modeling in Risk-Based Applications

Abstract: With the development of the financial industry, credit default prediction, as an important task in financial risk management, has received increasing attention. Traditional credit default ...
IEEE

Model Predictive Control of Pneumatic Artificial Muscle Antagonist Joint Angle Tracking Based on BP Neural Network Modelling

Abstract: A back propagation neural network prediction method is designed for the predictive control of joint angles in pneumatic artificial muscles in this paper, aimed at improving trajectory ...
C&EN

Efficient Molecular Crystal Structure Prediction and Stability Assessment with AIMNet2 Neural Network Potentials

Department of Materials Science and Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania 15213, United States Department of Chemistry, Carnegie Mellon University, 5000 ...
eLife

Center-surround inhibition by expectation: a neuro-computational account

This is a methodologically rich manuscript that is important for revealing the center-surround inhibition profile of expectation in orientation space. The analyses are compelling in validating the ...
Frontiers

The nature of quantum parallel processing and its implications for coding in brain neural networks: a novel computational mechanism

Conventionally it is assumed that the nerve impulse is an electrical process based upon the observation that electrical stimuli produce an action potential as defined by Hodgkin Huxley (1952) (HH).
C&EN

Grand-Canonical Equivariant Neural Potentials for Electrochemical Interfaces

State Key Laboratory of Precision and Intelligent Chemistry, University of Science and Technology of China, Hefei, Anhui 230026, China Department of Chemical Physics, School of Chemistry and Materials ...