Research map / Time series / Causal and generative time series
Latent Laplace Diffusion for Irregular Multivariate Time Series
Zinuo You, Jin Zheng, John Cartlidge
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 |
|---|---|---|---|
| add history conditioning (ablation) | LLapDiff · NOAA US longest horizons | CRPS: 1.450 -> 0.440 | Improved |
| add learned poles (ablation) | LLapDiff · NOAA US longest horizons | CRPS: 1.310 -> 0.440 | Improved |
| add latent space diffusion (ablation) | LLapDiff · NOAA US longest horizons | CRPS: 1.030 -> 0.440 | Improved |
| pretrain summarizer instead of joint training (ablation) | LLapDiff · NOAA US longest horizons | CRPS: 1.360 -> 0.440 | Improved |
| add history conditioning (ablation) | LLapDiff · BMS Air longest horizons | CRPS: 0.816 -> 0.516 | Improved |
| add learned poles (ablation) | LLapDiff · US Equity longest horizons | CRPS: 0.476 -> 0.406 | Improved |
| add temporal token (gap encoding) (ablation) | LLapDiff · NOAA UK longest horizons | CRPS: 1.837 -> 0.557 | Improved |
| add dynamics token (ablation) | LLapDiff · NOAA UK longest horizons | CRPS: 1.037 -> 0.557 | Improved |
| add port token (ablation) | LLapDiff · NOAA UK longest horizons | CRPS: 1.247 -> 0.557 | Improved |
| raise minimum timestamp coverage threshold from 0% to 80% (ablation) | LLapDiff · NOAA US longest horizon | CRPS: 0.440 -> 0.900 | Hurt |
| raise minimum timestamp coverage threshold from 0% to 80% (ablation) | LLapDiff · Crypto longest horizon | CRPS: 0.350 -> 0.380 | No clear effect |
| increase DDIM steps from 16 to 64 (ablation) | LLapDiff · NOAA-US longest horizon | CRPS: 0.4554 -> 0.4400 | Improved |
Closest papers by meaning
- Latent Diffusion Transformer for Probabilistic Time Series Forecasting (AAAI 2024 · similarity 0.88)
- Non-stationary Diffusion For Probabilistic Time Series Forecasting (ICML 2025 · similarity 0.88)
- Auto-Regressive Moving Diffusion Models for Time Series Forecasting (AAAI 2025 · similarity 0.88)
- Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models (ICLR 2025 · similarity 0.87)
- ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space (NeurIPS 2026 · similarity 0.87)
- Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs (ICLR 2025 · similarity 0.87)
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.
