Birla AI Labs Launches Yug-1, a Time Series Foundation Model Built in India

Birla AI Labs, an AI initiative and venture studio under the Aditya Birla Group, has released Yug-1, its first time series foundation model (TSFM), developed to forecast outcomes, identify patterns, and detect anomalies across interconnected datasets.

TSFMs are large-scale AI models pre-trained on a diverse collection of universal temporal patterns, such as weather, traffic, finance, retail, and energy records.

Ananya Birla, Founder and Chairperson of Birla AI Labs, said Yug-1 outperformed other first-generation TSMFs on the GiftEval benchmark and performed competitively against newer-generation models.

The company said its frontier research team took Yug-1 from training to deployment in under six months. The model is available on GitHub and Hugging Face for developers and researchers to test.

“Most of the conversation around AI today is about language. But so much of the data that actually runs businesses and economies moves through time,” Birla wrote in a LinkedIn post.

She cited demand and supply, equipment performance, financial signals, and infrastructure usage as examples of data where understanding patterns over time can inform business decisions.

Yug-1 is built to analyse such time-dependent data and generate forecasts across multiple variables. Time series models are used in applications such as demand forecasting, financial analysis, equipment monitoring, and infrastructure planning.

Birla AI Labs described Yug-1 as Asia’s first TSMF built for real-world use. The claim positions the release as an effort to expand AI research beyond language models to systems that analyse structured, time-dependent data.

The company’s research team presented its work at NeurIPS 2025, ICML 2026, and the World Summit AI, as well as at university campuses in India, Europe, and the UK.

“When we started the research arm of Birla AI Labs, the belief was simple: research only matters when it reaches the real world,” Birla said.

She added that the team plans to present Yug-1 at NeurIPS 2026 and engage with university campuses and research labs globally in the coming months.

Birla also encouraged developers to test the model and provide feedback, which she said would help shape its future development.