Skip to content Skip to sidebar Skip to footer

AI Shorts

Transforming Long-Duration Multivariable Time-Series Prediction: Presenting PDETime, a Unique Machine Learning Strategy Utilizing Neural PDE Solvers for Matchless Precision

A team of researchers from the Harbin Institute of Technology, Huawei Technologies Ltd, Squirrel AI, Meta AI, and Fudan University have developed a groundbreaking model for multivariate time series forecasting called PDETime. Traditional forecasting models, used in various applications from weather prediction to energy management, tend to rely on historical data and simple time-index features,…

Read More

Stanford researchers present Score Entropy Discrete Diffusion (SEDD): A machine learning model that contests the autoregressive language pattern and outperforms GPT-2 in terms of complexity and quality.

Artificial Intelligence (AI) and Deep Learning have made significant advancements, particularly in the area of generative modelling, a subfield of Machine Learning. Here, models are trained to produce new data samples that match the training data. Generative AI systems have shown remarkable capabilities, such as creating images from written descriptions and solving complex problems. Autoregressive…

Read More

Introducing PlanGPT: The Pioneering Large-Scale Language Model Framework for Tackling Challenges in Urban Planning and Spatial Development.

The urban and spatial planning sector is a rapidly evolving field that increasingly requires the integration of advanced technology. This not only expedites planning processes, but also improves the precision and efficacy of urban development strategies. Amid this technological revolution, the advent of specialised large language models (LLMs), designed for specific industries, has occurred. This…

Read More