LiteRT.js runs machine learning models locally with CPU, GPU and emerging NPU acceleration, potentially reducing server infrastructure, inference charges and data movement.
Fusing Time Series and Tweet Semantics: A Cross-Modal LLM Framework for Topic Popularity Forecasting
Abstract: Accurate topic popularity forecasting on social media is critical for understanding public dynamics but challenged by irregular patterns and data scarcity. While large language models (LLMs) ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results