Research map / Probabilistic and scientific modeling / Molecules and proteins
Imitative Non-Autoregressive Modeling for Trajectory Forecasting and Imputation
Mengshi Qi, Jie Qin, Yu Wu, Yi Yang
Check 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 the full imitative non-autoregressive model instead of the strongest listed prediction baseline | Trajectory forecasting · PEMS-SF Traffic | P-L2: 8.92 -> 5.22 | Improved |
| Use the full imitative non-autoregressive model instead of the strongest listed prediction baseline | Trajectory forecasting · Billiards | P-L2: 5.59 -> 3.05 | Improved |
| Use the full imitative non-autoregressive model instead of the strongest listed prediction baseline | Trajectory forecasting · Basketball Tracking | P-L2: 2.66 -> 1.79 | Improved |
| Use the full imitative non-autoregressive model instead of NAOMI | Sequence imputation · PEMS-SF Traffic | I-L2: 3.54 -> 2.72 | Improved |
| Use the full imitative non-autoregressive model instead of NAOMI | Sequence imputation · Billiards | I-L2: 0.067 -> 0.052 | Improved |
| Use the full imitative non-autoregressive model instead of NAOMI | Sequence imputation · Basketball Tracking | I-L2: 0.423 -> 0.323 | Improved |
| Add imitation learning from the RC-VAE demonstrator (ablation) | NART sequence imputation · PEMS-SF Traffic | I-L2: 3.66 -> 2.72 | Improved |
| Add imitation learning from the RC-VAE demonstrator (ablation) | NART sequence imputation · Billiards | I-L2: 0.065 -> 0.052 | Improved |
| Add imitation learning from the RC-VAE demonstrator (ablation) | NART sequence imputation · Basketball Tracking | I-L2: 0.412 -> 0.323 | Improved |
| Add imitation learning from the RC-VAE demonstrator (ablation) | NART sequence imputation · Billiards | Wall: 0.159 -> 0.030 | Improved |
| Add imitation learning from the RC-VAE demonstrator (ablation) | NART sequence imputation · Basketball Tracking | Path-L: 2.356 -> 1.922 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NAOMI — NAOMI: Non-Autoregressive Multiresolution Sequence Imputation (NeurIPS 2019) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation (ICML 2025 · similarity 0.86)
- MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation (CVPR 2025 · similarity 0.86)
- Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking (NeurIPS 2024 · similarity 0.86)
- AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models (CVPR 2026 · similarity 0.86)
- Zero-shot Imputation with Foundation Inference Models for Dynamical Systems (ICLR 2025 · similarity 0.86)
- MS-TIP: Imputation Aware Pedestrian Trajectory Prediction (ICML 2024 · 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.
