Birla AI Labs launches Yug-1, a time-series foundation model built in India
Birla AI Labs, the Aditya Birla Group's AI initiative and venture studio, has released Yug-1, its first time-series foundation model, Analytics India Magazine reports. Time-series foundation models are pre-trained on temporal patterns such as weather, traffic, finance, retail and energy records; Yug-1 is built to forecast outcomes, identify patterns and detect anomalies across interconnected datasets. Founder and chairperson Ananya Birla said Yug-1 outperformed other first-generation time-series foundation models on the GiftEval benchmark and performed competitively against newer-generation models; these are company-reported results, not independent evaluations. The lab said its frontier research team took the model from training to deployment in under six months. Yug-1 is available on GitHub and Hugging Face for developers and researchers to test.
DTT summary based on Analytics India Magazine's report. The full article is on the publisher's site.
Yug-1, Birla AI Labs' first time-series foundation model (TSFM)
Birla AI Labs, Aditya Birla Group's AI initiative and venture studio
Outperforms first-generation TSFMs on GiftEval (company-reported)
GitHub and Hugging Face
Training to deployment in under six months
