Ievgen Redko

CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data

Multi-path reasoning on a budget: towards theoretically optimal hyperparameter-free adaptive self-consistency

Which transformers components are the most sensitive to distribution shifts?

TiViT: Time Series Representations Lie Hidden in Pretrained Vision Transformers

Zero-shot Model-based Reinforcement Learning using Large Language Models

Large Language Models as Markov Chains