Research map / Probabilistic and scientific modeling / Molecules and proteins
Introducing Probabilistic Bézier Curves for N-Step Sequence Prediction
Ronny Hug, Wolfgang Hübner, Michael Arens
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 |
|---|---|---|---|
| replace Particle LSTM with N-Curve MDN | trajectory prediction · SDD hyang | FDE: 0.129 -> 0.088 | Improved |
| replace Particle LSTM with N-Curve MDN | trajectory prediction · SDD hyang | NLL: 18.552 -> -4.760 | Improved |
| replace LSTM-BMS with N-Curve MDN | trajectory prediction · SDD deathcircle | FDE: 0.483 -> 0.314 | Improved |
| replace RGP with N-Curve MDN | motion capture sequence prediction · CMU walking | RMSE: 0.822 -> 0.794 | Improved |
| replace MLP with N-Curve MDN | motion capture sequence prediction · CMU walking | RMSE: 0.911 -> 0.794 | Improved |
Closest papers by meaning
- (How) Can Transformers Predict Pseudo-Random Numbers? (ICML 2025 · similarity 0.79)
- Bezier Everywhere All at Once: Learning Drivable Lanes as Bezier Graphs (CVPR 2024 · similarity 0.78)
- Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves (ICML 2025 · similarity 0.78)
- Decomposable Transformer Point Processes (NeurIPS 2024 · similarity 0.77)
- On the Expressive Power of Tree-Structured Probabilistic Circuits (NeurIPS 2024 · similarity 0.77)
- Sequence Modeling with Spectral Mean Flows (NeurIPS 2025 · similarity 0.77)
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.
