Author

Mo-Kai Pan

1 paper indexed here

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 Sep 2026

QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning

This work proposes QAMM, a method that turns the critic-derived adjoint signal into supervision for MeanFlow's average velocity, and derives the adjoint MeanFlow target, specify its gradient boundaries, and train it with an offline actor-critic.

Yu Gong, Shu-Tong Ding, Mo-Kai Pan et al. · 0 citations