# ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification

arXiv: https://arxiv.org/abs/2605.22684 · HTML: https://mlsanity.com/paper/2605.22684/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 10 of 10)

- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [Nested Learning: The Illusion of Deep Learning Architectures](https://mlsanity.com/paper/2512.24695/) (2025)
- [A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting](https://mlsanity.com/paper/2407.15909/) (2024)

## Abstract (arXiv)

Time Series Foundation Models (TSFMs) have become a new component of the state-of-the-art in general time series forecasting. However, adapting them to specialized classification tasks remains constrained by two interconnected challenges: the quadratic cost of standard attention mechanisms and the inability to disentangle the structural components underlying time series variability. This technical report introduces ChronoVAE-HOPE, a next-generation TSFM that reconciles massive generalization with structured latent representation for time series classification. The core of the proposal is a Variational Autoencoder (VAE) framework built upon the HOPE Block, which replaces quadratic attention with a dual-memory system: Titans modules for dynamic short-term retention and a Continuum Memory System (CMS) for the abstraction of long-term historical context. A key architectural novelty is the disentangled latent space, which factorizes representations into independent trend and seasonal components via dedicated encoder heads and separate decoder pathways. ChronoVAE-HOPE undergoes self-supervised pre-training on the Monash archive, combining a Masked Time Series Modeling (MTSM) auxiliary objective with a disentangled VAE reconstruction loss. The pre-trained encoder is subsequently frozen and used to generate fixed-length embeddings for downstream classification on the UCR benchmark datasets. Empirical results demonstrate strong performance across diverse temporal domains, particularly in settings characterized by strict causal structure. ChronoVAE-HOPE establishes a robust and interpretable framework for the adaptation of foundation models to time series classification through structured generative representations.