Late Time

"Late time" in various scientific contexts refers to the analysis of phenomena after an initial transient phase, focusing on long-term behavior and asymptotic properties. Current research emphasizes developing efficient models, such as physics-informed neural networks and equivariant networks, to analyze this late-time behavior in diverse fields including material science, medical imaging (e.g., diffusion MRI and retinal imaging), and time series analysis. These advancements improve prediction accuracy and computational efficiency, impacting areas like radiation damage modeling, disease diagnosis, and time series forecasting.

Papers

November 13, 2024

The Systems Engineering Approach in Times of Large Language Models
Christian Cabrera, Viviana Bastidas, Jennifer Schooling, Neil D. Lawrence
Artificial Intelligence Engineering System Late Time System Engineering

October 18, 2024

Harnessing Causality in Reinforcement Learning With Bagged Decision Times
Daiqi Gao, Hsin-Yu Lai, Predrag Klasnja, Susan A. Murphy
Reinforcement Learning Markov Decision Process Late Time Piecewise Deterministic Markov Process

May 15, 2024

Sign of the Times: Evaluating the use of Large Language Models for Idiomaticity Detection
Dylan Phelps, Thomas Pickard, Maggie Mi, Edward Gow-Smith, Aline Villavicencio
Large Language Model Greater Public Use Cultural Sign Idiomaticity Detection Late Time

April 30, 2024

Training a high-performance retinal foundation model with half-the-data and 400 times less compute
Justin Engelmann, Miguel O. Bernabeu
Foundation Model Pre Trained Model Limited Field Retinal Imaging Late Time

December 25, 2023

TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning
Jiexi Liu, Songcan Chen
Contrastive Learning Self Supervised Contrastive Learning Time Series Representation Late Time

November 1, 2023

Accelerating Electronic Stopping Power Predictions by 10 Million Times with a Combination of Time-Dependent Density Functional Theory and Machine Learning
Logan Ward, Ben Blaiszik, Cheng-Wei Lee, Troy Martin, Ian Foster, André Schleife
Neural Network Machine Learning New Combination Atomic Knowledge Material Informatics Energy Deposition Kohn Sham Quantum Material Late Time

July 12, 2023

Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning
Gengyuan Zhang, Yurui Zhang, Kerui Zhang, Volker Tresp
Vision Language Model Full Model Visual Encoder Temporal Reasoning Generative Vision Language Model Location Analysis Late Time

May 6, 2023

Simulation and Prediction of Countercurrent Spontaneous Imbibition at Early and Late Times Using Physics-Informed Neural Networks
Jassem Abbasi, Pål Østebø Andersen
Human Prediction Physic Informed Neural Network Simulation Study Physic Informed Loss Porous Medium Late Time

April 12, 2023

$E(3) \times SO(3)$-Equivariant Networks for Spherical Deconvolution in Diffusion MRI
Axel Elaldi, Guido Gerig, Neel Dey
Equivariant Network Diffusion MRI Spherical Convolution Late Time

February 20, 2023

FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification
Mingyue Cheng, Qi Liu, Zhiding Liu, Zhi Li, Yucong Luo, Enhong Chen
Temporal Attention Hierarchical Representation Transformer Encoder Multi Scale Representation Multivariate Time Series Classification Late Time

November 3, 2022

$2 \times 2$ Zero-Sum Games with Commitments and Noisy Observations
Ke Sun, Samir M. Perlaza, Alain Jean-Marie
Nash Equilibrium Game Content Zero Sum Game Noisy Observation Stackelberg Equilibrium Late Time CoMMIT Selection

March 30, 2022

Unseen Classes at a Later Time? No Problem
Hari Chandana Kuchibhotla, Sumitra S Malagi, Shivam Chandhok, Vineeth N Balasubramanian
Generalization Performance Zero Shot Learning Right Problem Unseen Class Late Time Bidirectional Alignment GZSL Method

January 16, 2022

YOLO -- You only look 10647 times
Christian Limberg, Andrew Melnik, Augustin Harter, Helge Ritter
Image Classification Model YOLO Shake Hand Region Proposal Stage Object Detection Late Time

Late Time

Papers

The Systems Engineering Approach in Times of Large Language Models

Harnessing Causality in Reinforcement Learning With Bagged Decision Times

Sign of the Times: Evaluating the use of Large Language Models for Idiomaticity Detection

Training a high-performance retinal foundation model with half-the-data and 400 times less compute

TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning

Accelerating Electronic Stopping Power Predictions by 10 Million Times with a Combination of Time-Dependent Density Functional Theory and Machine Learning

Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning

Simulation and Prediction of Countercurrent Spontaneous Imbibition at Early and Late Times Using Physics-Informed Neural Networks

$E(3) \times SO(3)$-Equivariant Networks for Spherical Deconvolution in Diffusion MRI

FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification

$2 \times 2$ Zero-Sum Games with Commitments and Noisy Observations

Unseen Classes at a Later Time? No Problem

YOLO -- You only look 10647 times