Birla AI Labs, an AI initiative and venture studio under the Aditya Birla Group, has launched Yug-1, its first time series foundation model. The model is designed to forecast outcomes, identify patterns and detect unusual changes in data collected over time.
Yug-1 Focuses on Data That Changes Over Time
Time series foundation models analyse patterns in data such as weather records, traffic, financial activity, retail sales and energy use. They can help businesses forecast demand, monitor equipment, analyse financial trends and plan infrastructure.
Ananya Birla, founder and chairperson of Birla AI Labs, said Yug-1 outperformed other first-generation time series foundation models on the GiftEval benchmark. She also said it performed competitively against newer-generation models.
From Research to Deployment in Under Six Months
Birla AI Labs said its research team developed Yug-1 from training to deployment in under six months. The model is available on GitHub and Hugging Face, where developers and researchers can access and test it.
Birla said much of the current discussion around AI focuses on language. However, businesses also rely on data that changes over time, such as demand, supply, equipment performance and financial activity. Analysing these patterns can help organisations make better-informed decisions.
Yug-1 is designed to study this type of data and produce forecasts across multiple variables. Birla AI Labs describes it as Asia’s first time series foundation model built for real-world use. This claim has been made by the company.
Birla AI Labs Plans Further Research Engagements
The company’s research team has presented its work at NeurIPS 2025, ICML 2026 and the World Summit AI. It has also shared its research at university campuses in India, Europe and the UK.
Birla AI Labs plans to present Yug-1 at NeurIPS 2026 and engage with universities and research laboratories around the world. Birla has also encouraged developers to test the model and share feedback to support its future development.
