# Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models

arXiv: https://arxiv.org/abs/1808.04768 · HTML: https://mlsanity.com/paper/1808.04768/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2018.

## Built on by (most cited first, 12 of 12)

- [Planning Goals for Exploration](https://mlsanity.com/paper/2303.13002/) (2023)
- [On the link between conscious function and general intelligence in humans and machines](https://mlsanity.com/paper/2204.05133/) (2022)
- [Variational Predictive Routing with Nested Subjective Timescales](https://mlsanity.com/paper/2110.11236/) (2021)
- [CompILE: Compositional Imitation Learning and Execution](https://mlsanity.com/paper/1812.01483/) (2018)
- [Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos](https://mlsanity.com/paper/2411.08753/) (2024)
- [Learning Intuitive Physics with Multimodal Generative Models](https://mlsanity.com/paper/2101.04454/) (2021)
- [Long-horizon video prediction using a dynamic latent hierarchy](https://mlsanity.com/paper/2212.14376/) (2022)
- [InfoCon: Concept Discovery with Generative and Discriminative Informativeness](https://mlsanity.com/paper/2404.10606/) (2024)
- [Piecewise-constant Neural ODEs](https://mlsanity.com/paper/2106.06621/) (2021)
- [Towards Cost Sensitive Decision Making](https://mlsanity.com/paper/2410.03892/) (2024)
- [Bayesian sense of time in biological and artificial brains](https://mlsanity.com/paper/2201.05464/) (2022)
- [MHWA: Multi-timescale Hierarchical World-Action Model](https://mlsanity.com/paper/2610.14727/) (2026)

## Abstract (arXiv)

We introduce a method which enables a recurrent dynamics model to be temporally abstract. Our approach, which we call Adaptive Skip Intervals (ASI), is based on the observation that in many sequential prediction tasks, the exact time at which events occur is irrelevant to the underlying objective. Moreover, in many situations, there exist prediction intervals which result in particularly easy-to-predict transitions. We show that there are prediction tasks for which we gain both computational efficiency and prediction accuracy by allowing the model to make predictions at a sampling rate which it can choose itself.