Research map / Probabilistic and scientific modeling / Variational and generative sampling
A Variational Auto-Encoder Model for Stochastic Point Processes
Check 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 |
|---|---|---|---|
| add a learned, history-conditioned prior (ablation) | APP-VAE · Breakfast | accuracy: 27.09 -> 62.20 | Helped |
| add a learned, history-conditioned prior (ablation) | APP-VAE · MultiTHUMOS | accuracy: 8.79 -> 39.30 | Helped |
| add a learned, history-conditioned prior (ablation) | APP-VAE · Breakfast | LL: ≥-9.427 -> ≥-5.944 | Helped |
| add a learned, history-conditioned prior (ablation) | APP-VAE · MultiTHUMOS | LL: ≥-5.344 -> ≥-3.838 | Helped |
| add a learned, history-conditioned prior (ablation) | APP-VAE · Breakfast | MAE: 270.75 -> 142.65 | Helped |
| add a learned, history-conditioned prior (ablation) | APP-VAE · MultiTHUMOS | MAE: 2.02 -> 1.89 | Helped |
| increase latent dimension from 32 to 64 (ablation) | APP-VAE · MultiTHUMOS | LL: -4.486 -> -3.947 | Helped |
| increase latent dimension from 64 to 128 (ablation) | APP-VAE · MultiTHUMOS | LL: -3.947 -> -3.940 | No clear effect |
| increase latent dimension from 128 to 256 (ablation) | APP-VAE · MultiTHUMOS | LL: -3.940 -> -3.838 | Helped |
| increase latent dimension from 256 to 512 (ablation) | APP-VAE · MultiTHUMOS | LL: -3.838 -> -4.098 | Hurt |
| use mode selection instead of averaging predictions | APP-VAE · Breakfast | accuracy: 59.02 -> 62.20 | Helped |
| use synchronous constant-frame-rate prediction instead of asynchronous prediction (ablation) | APP-LSTM · Breakfast | accuracy: 61.39% vs 28.24% | Hurt |
Closest papers by meaning
- A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs (AAAI 2024 · similarity 0.88)
- Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models (ICML 2025 · similarity 0.85)
- Can't Make an Omelette Without Breaking Some Eggs: Plausible Action Anticipation Using Large Video-Language Models (CVPR 2024 · similarity 0.85)
- Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis (ICLR 2025 · similarity 0.84)
- AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos? (ICLR 2024 · similarity 0.84)
- Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling (ICML 2025 · similarity 0.84)
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.