Marcel Kollovieh

Discrete Bayesian Sample Inference for Graph Generation

Edit-Based Flow Matching for Temporal Point Processes

Generative Modeling with Bayesian Sample Inference

Byte Pair Encoding for Efficient Time Series Forecasting

Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling

Unlocking Point Processes through Point Set Diffusion

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting

TreeGen: A Bayesian Generative Model for Hierarchies

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging