Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational Temporal Abstraction
Taesup Kim, Sungjin Ahn, Yoshua Bengio
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use HRSSM instead of RSSM as the imagination model | Imagination-augmented agent · 3D maze goal-oriented navigation | reward | Improved |
| Discover temporal structure with HRSSM instead of RSSM | 3D maze sequence modeling · 3D maze | ELBO | No clear effect |
| Remove the prior on temporal structure (ablation) | HRSSM · Bouncing balls | temporal structure discovery | Hurt |
| Use a CNN-based rather than an RNN-based sequence decomposer (ablation) | HRSSM sequence decomposition · Sequence decomposition | sequence decomposition performance | Improved |
Closest papers by meaning
- Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models (NeurIPS 2018 · similarity 0.86)
- Moment-Based Variational Inference for Markov Jump Processes (ICML 2019 · similarity 0.82)
- Temporal-Difference Variational Continual Learning (NeurIPS 2025 · similarity 0.81)
- A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs (AAAI 2024 · similarity 0.81)
- Amodal Completion via Progressive Mixed Context Diffusion (CVPR 2024 · similarity 0.81)
- Continuity Laws for Sequential Models (NeurIPS 2026 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
