Author

Michael W. Mahoney

h-index 11 View on Semantic Scholar

We have 2 of 22 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Coarse-Graining Optimal Transport for Rollout-Free Post-Training of Flow Matching

ReCouple is introduced, a controllable framework that constructs coarse-grained OT couplings, to better understand rollout-free OT-based post-training post-training quality, and reveals an NFE-dependent interplay between coupling optimality, neural realizability, and generation quality.

Soon Hoe Lim, Aditi Gupta, Michael W. Mahoney et al. · 0 citations

#machine learning Feb 2026

Is Flow Matching Just Trajectory Replay for Sequential Data?

This work derives the optimal velocity field targeted by the empirical FM objective on sequential data and shows that the resulting sampler is an ODE whose dynamics describe a nonparametric, memory-augmented continuous-time dynamical system.

Soon Hoe Lim, Shi-Zhen Lin, Michael W. Mahoney et al. · arXiv.org · 4 citations