Continuous-Time Trajectory Generation from Discrete Observations with Stochasticity
stat.ML, cs.LG, math.DS
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/R1fe/PhiBE-Flow
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Likelihood Training of Schr\"odinger Bridge using Forward-Backward SDEs Theory
- Stochastic Adversarial Video Prediction
- Geometry-Preserving Encoder/Decoder in Latent Generative Models
- Video (language) modeling: a baseline for generative models of natural videos
- Score-Based Generative Modeling through Stochastic Differential Equations
- Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
- Towards Accurate Generative Models of Video: A New Metric & Challenges
- VideoGPT: Video Generation using VQ-VAE and Transformers
- PhiBE: A PDE-based Bellman Equation for Continuous Time Policy Evaluation
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier