Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Is Flow Matching Just Trajectory Replay for Sequential Data?
Soon Hoe Lim, Shizheng Lin, Michael W. Mahoney +1
Flow matching (FM) is increasingly used in scientific domains for time series generation and forecasting, where data often arise from underlying dynamical systems. However, it is n…
stat.ML2026
Quantifying Epistemic Uncertainty in Diffusion Models
Aditi Gupta, Raphael A. Meyer, Yotam Yaniv +2
To ensure high quality outputs, it is important to quantify the epistemic uncertainty of diffusion models. Existing methods are often unreliable because they mix epistemic and alea…
stat.ML2025
Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting
Soon Hoe Lim, Yijin Wang, Annan Yu +4
Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces. However, the impa…