mlsanityData to 7 Oct 2026

Variational Temporal Abstraction

arXiv 1910.00775 ↗First posted 2 Oct 2019cs.LG cs.AI stat.MLcited by 37

Not on the map. Why?

Abstract (arXiv)

We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state transition hierarchically. We also propose to apply this model to implement the jumpy-imagination ability in imagination-augmented agent-learning in order to improve the efficiency of the imagination. In experiments, we demonstrate that our proposed method can model 2D and 3D visual sequence datasets with interpretable temporal structure discovery and that its application to jumpy imagination enables more efficient agent-learning in a 3D navigation task.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 11; 2023: 6; 2024: 8; 2025: 2; 2026: 2.

37 papers.

Sort:

By area:

  1. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  2. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  3. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  4. 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 181
  5. 2025Reinforcement Learning with Action Chunkingcited by 97
  6. 2024Simple Hierarchical Planning with Diffusioncited by 71
  7. 2022Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Modelscited by 53
  8. 2021Clockwork Variational Autoencoderscited by 40
  9. 2022Learning Options via Compressioncited by 22
  10. 2021Subgoal Search For Complex Reasoning Taskscited by 21
  11. 2021Deep Explicit Duration Switching Models for Time Seriescited by 17
  12. 2023Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Modelcited by 16
25 more
  1. 2022Unsupervised Learning of Temporal Abstractions with Slot-based Transformerscited by 14
  2. 2024Leveraging Skills from Unlabeled Prior Data for Efficient Online Explorationcited by 13
  3. 2022Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Searchcited by 12
  4. 2024Language-guided Skill Learning with Temporal Variational Inferencecited by 11
  5. 2021Variational Predictive Routing with Nested Subjective Timescalescited by 9
  6. 2024Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Expertscited by 9
  7. 2024Exploring the limits of Hierarchical World Models in Reinforcement Learningcited by 9
  8. 2023LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Followingcited by 8
  9. 2022Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learningcited by 7
  10. 2023Hybrid Search for Efficient Planning with Completeness Guaranteescited by 6
  11. 2024PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performercited by 6
  12. 2021A Temporal Variational Model for Story Generationcited by 5
  13. 2022Multi-View Dreaming: Multi-View World Model with Contrastive Learningcited by 5
  14. 2022Long-horizon video prediction using a dynamic latent hierarchycited by 4
  15. 2023Model-Based Reinforcement Learning with Isolated Imaginationscited by 4
  16. 2024Identifying Selections for Unsupervised Subtask Discoverycited by 4
  17. 2021Conditional COT-GAN for Video Prediction with Kernel Smoothingcited by 3
  18. 2026Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systemscited by 3
  19. 2021Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithmcited by 2
  20. 2022Learning to Express in Knowledge-Grounded Conversationcited by 2
  21. 2024Nonstationary Time Series Forecasting via Unknown Distribution Adaptationcited by 2
  22. 2022Bayesian sense of time in biological and artificial brainscited by 1
  23. 2023Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learningcited by 1
  24. 2025Real-World Robot Control by Deep Active Inference With a Temporally Hierarchical World Modelcited by 0
  25. 2026SUNTA: Hierarchical Video Prediction with Surprise-based Chunkingcited by 0