Transferring Knowledge from Large Foundation Models to Small Downstream Models

Documenti analoghi

• Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
  di: Yu, Annan, et al.
  Pubblicazione: (2025)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
  di: Masserano, Luca, et al.
  Pubblicazione: (2024)
• Large Language Models Are Zero-Shot Time Series Forecasters
  di: Gruver, Nate, et al.
  Pubblicazione: (2023)
• Gradient-Free Generation for Hard-Constrained Systems
  di: Cheng, Chaoran, et al.
  Pubblicazione: (2024)
• Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
  di: Yu, Annan, et al.
  Pubblicazione: (2025)