Pacific Ocean
Backdoor Attacks on Multivariate Time Series Forecasting
Unlike traditional backdoor attacks that focus on specific class labels, our approach aims to induce poisoned models to predict future data as a predefined target pattern.
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
By introducing LLM-embedded textual timestamps, Auto-Times can utilize chronological information to align multivariate time series. Empirically, AutoTimes achieves state-of-the-art with 0.1% trainable parameters and
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
Lately, there has been a surge in interest surrounding generative modeling of time series data. Most existing approaches are designed either to process short sequences or to handle long-range sequences. This dichotomy can be attributed to gradient issues with recurrent networks, computational costs associated with transformers, and limited expressiveness of state space models. Towards a unified generative model for varying-length time series, we propose in this work to transform sequences into images.
The Sea Surface Height Edition J. Emmanuel Johnson
The ocean is a crucial component of the Earth's system.
Learning from Highly Sparse Spatio-temporal Data
Incomplete spatio-temporal data in the real world has spawned much research.
StyleDrop: Text-to-Image Generation in Any Style Kihyuk Sohn Nataniel Ruiz Kimin Lee Daniel Castro Chin Irina Blok Huiwen Chang
Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts.