Research map / Time series / Causal and generative time series
Sequential Neural Processes
Gautam Singh, Jaesik Yoon, Youngsung Son, Sungjin Ahn
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 temporal latent transitions conditioned on past latents and current context instead of an independent per-task latent | SNP vs NP · Dynamic GP regression, task (a) | target NLL | Improved |
| Use temporal latent transitions conditioned on past latents and current context instead of an independent per-task latent | SNP vs NP · Dynamic GP regression, tasks (b) and (c) | target NLL | Improved |
| Use TGQN's temporal latent transitions rather than GQN's single rollout latent | TGQN vs GQN · 2D and 3D dynamic scenes | NLL | Improved |
| Use TGQN's temporal latent transitions rather than GQN's single rollout latent | TGQN vs GQN · 2D and 3D dynamic scenes | pixel MSE | Improved |
| Use TGQN rather than GQN for prediction beyond the training horizon | TGQN vs GQN · Dynamic scene prediction | pixel MSE | Improved |
| Use posterior dropout during training (ablation) | TGQN · 2D and 3D dynamic scenes | pixel MSE | Improved |
| Use posterior dropout during training (ablation) | TGQN · 2D and 3D dynamic scenes | NLL | Hurt |
| Use posterior dropout during training (ablation) | SNP · 1D regression | training success | No clear effect |
| Use temporal latent transitions rather than GQN's single rollout latent | TGQN vs GQN · Dynamic scene tracking | generation quality over observed time-steps | Improved |
Closest papers by meaning
- Learning Dynamic Generator Model by Alternating Back-Propagation through Time (AAAI 2019 · similarity 0.86)
- Interacting Diffusion Processes for Event Sequence Forecasting (ICML 2024 · similarity 0.84)
- Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models (ICLR 2025 · similarity 0.84)
- EasyTPP: Towards Open Benchmarking Temporal Point Processes (ICLR 2024 · similarity 0.84)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.84)
- Flow Matching Neural Processes (NeurIPS 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.
