Research map / Probabilistic and scientific modeling / Variational and generative sampling
Auto-Encoding Sequential Monte Carlo
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 AESMC with SMC instead of IWAE with importance sampling | VRNN on Moving Agents · Moving Agents | ELBO | Helped |
| Increase the number of particles during training (ablation) | AESMC on the LGSSM · LGSSM | model-learning convergence | Helped |
| Increase the number of particles during training (ablation) | proposal learning on the LGSSM · LGSSM | inference quality | Hurt |
| Increase the number of particles at test time (ablation) | inference using the learned proposal on the LGSSM · LGSSM | inference quality | Helped |
| Use alternating ELBOs, with SMC and many particles for model updates and IS and few particles for proposal updates (ablation) | AESMC · LGSSM | model and proposal learning | Helped |
| Use alternating ELBOs (ablation) | AESMC · Moving Agents | ELBO | Mixed |
| Include REINFORCE terms for discrete ancestor choices (ablation) | AESMC gradient estimation · AESMC training | gradient-estimator variance | Hurt |
Closest papers by meaning
- Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo (ICML 2024 · similarity 0.86)
- Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo (ICLR 2025 · similarity 0.86)
- Online Variational Sequential Monte Carlo (ICML 2024 · similarity 0.86)
- Ensembling Language Models with Sequential Monte Carlo (NeurIPS 2026 · similarity 0.85)
- Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models (NeurIPS 2026 · similarity 0.85)
- AutoStep: Locally adaptive involutive MCMC (ICML 2025 · similarity 0.85)
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.