Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
cs.CV, cs.AI, cs.LG
Submitted: 2025-09-30
Updated: 2026-11-07
Code: https://github.com/Sachithx/EntroPE
Terminology
Sources
- The UEA multivariate time series classification archive, 2018
- TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding
- Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
- ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs