arXiv Machine Learning June 18, 2026 By Shengyu Feng, Tarun Suresh, Yiming Yang

Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching

Read the original on arXiv Machine Learning →

arXiv:2605. 30920v2 Announce Type: replace Abstract: Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training with large collections of near-optimal solutions.

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

diffusion

arXiv Machine Learning

Jul 17

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

arXiv:2607. 14522v1 Announce Type: new Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC).

By Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang

llms diffusion reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 16

CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization

arXiv:2602. 08210v2 Announce Type: replace Abstract: Heatmap-based solvers have emerged as a promising paradigm for Combinatorial Optimization (CO).

By Hyungseok Song, Deunsol Yoon, Kanghoon Lee, Han-Seul Jeong, Soonyoung Lee, Woohyung Lim

diffusion reinforcement-learning fine-tuning benchmarks safety

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

Jun 2

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

arXiv:2604. 17838v2 Announce Type: replace Abstract: Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.

By Kijung Jeon, Michael Muehlebach, Molei Tao

diffusion robotics benchmarks safety

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 18

Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space

arXiv:2605. 17232v2 Announce Type: replace Abstract: Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology.

By Kelvin Kan, Xingjian Li, Benjamin J. Zhang, Tuhin Sahai, Stanley Osher, Markos A. Katsoulakis

diffusion

Related stories

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization

Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

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

Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space