This project compiles academic papers and implementations exploring how Large Language Models and foundation models can be adapted for time series analysis. It covers approaches like fine-tuning pretrained LLMs on time series data, prompt-based methods for forecasting, and techniques for representing temporal data for language models. The collection includes works such as PromptCast, Time-LLM, TEMPO, and others that achieve state-of-the-art results by repurposing language models for sequential data tasks.