Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting

arXiv:2601.12467 · cs.LG, cs.AI · Submitted 2026-01-18 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-01-18

Updated: 2026-10-18

Comments: 7 pages, 1 figure(s), 6 table(s)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 4× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 3 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Transformer Encoder — 1× in this paper · explained in 2 episodes
• Transformer Model — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks