arXiv Machine Learning July 3, 2026 By Carles Domingo-Enrich, Jiequn Han

Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control

Read the original on arXiv Machine Learning →

arXiv:2604. 08580v2 Announce Type: replace-cross Abstract: Reward fine-tuning of diffusion and flow models and sampling from tilted or Boltzmann distributions can both be formulated as stochastic optimal control (SOC) problems, where learning an optimal generative dynamics corresponds to optimizing a control under SDE constraints.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 15

Continuous Policy and Value Iteration for Stochastic Control Problems and Its Convergence

arXiv:2506. 08121v2 Announce Type: replace-cross Abstract: We introduce a continuous policy-value iteration algorithm where the approximations of the value function of a stochastic control problem and the optimal control are simultaneously updated through Langevin-type dynamics.

By Qi Feng, Gu Wang

arXiv Machine Learning

Jun 16

DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising

arXiv:2606. 15359v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for planning and control by learning multimodal distributions over actions and trajectories.

By Paolo Giaretta, Zeyang Li, Navid Azizan

diffusion multimodal benchmarks safety

arXiv Machine Learning

Jun 11

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies

arXiv:2601. 08136v2 Announce Type: replace Abstract: Diffusion and flow policies are gaining prominence in online reinforcement learning (RL) due to their expressive power, yet training them efficiently remains a critical challenge.

By Zeyang Li, Sunbochen Tang, Navid Azizan

diffusion reinforcement-learning benchmarks

arXiv Machine Learning

5d ago

Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces

arXiv:2511. 06239v2 Announce Type: replace-cross Abstract: Learning-based methods for sampling from the Gibbs distribution in finite-dimensional spaces have progressed quickly, yet theory and algorithmic design for infinite-dimensional function spaces remain limited.

By Byoungwoo Park, Juho Lee, Guan-Horng Liu

diffusion

arXiv Machine Learning

Jul 2

Goal-oriented learning of stochastic differential equations using error bounds on path-space observables

arXiv:2603. 20467v2 Announce Type: replace-cross Abstract: Stochastic differential equations (SDEs), which serve as the governing equations for dynamical systems in a broad range of applications, can become cost-prohibitive for numerical simulation at scales necessary for quantifying key properties.

By Joanna Zou, Han Cheng Lie, Youssef Marzouk

arXiv AI

Jun 19

Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach

arXiv:2602. 05533v3 Announce Type: replace Abstract: We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one.

By Zhengyi Guo, Wenpin Tang, Renyuan Xu

diffusion safety

Related stories

Continuous Policy and Value Iteration for Stochastic Control Problems and Its Convergence

DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies

Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces

Goal-oriented learning of stochastic differential equations using error bounds on path-space observables

Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach