Afshin Rostamizadeh

A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs

This Time is Different: An Observability Perspective on Time Series Foundation Models

Analyzing Similarity Metrics for Data Selection for Language Model Pretraining

A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs

No more hard-prompts: SoftSRV prompting for synthetic data generation