Active Flow Matching

2026-03-01 · Yashvir S. Grewal, Daniel M. Steinberg, Thang D. Bui, Cheng Soon Ong, Edwin V. Bonilla arxiv

Discrete diffusion and flow matching models capture complex, non-additive and non-autoregressive structure in high-dimensional objective landscapes through parallel, iterative refinement. However, their implicit generative nature precludes direct integration with principled variational frameworks for online black-box optimisation, such as variational search distributions (VSD) and conditioning by adaptive sampling (CbAS). We introduce Active Flow Matching (AFM), which reformulates variational objectives to operate on conditional endpoint distributions along the flow, enabling gradient-based steering of flow models toward high-fitness regions while preserving the rigour of VSD and CbAS. We derive forward and reverse Kullback-Leibler (KL) variants using self-normalised importance sampling. Across a suite of online protein and small molecule design tasks, forward-KL AFM consistently performs competitively compared to state-of-the-art baselines, demonstrating effective exploration-exploitation under tight experimental budgets.

📄 PDF Abstract BibTeX arXiv:2603.00877

Code (0)

등록된 구현이 없습니다.

Scalable Grid-Aware Dynamic Matching using Deep Reinforcement Learning

2023-01-31 · Majid Majidi, Deepan Muthirayan, Masood Parvania, Pramod P. Khargonekar

This paper proposes a two-level hierarchical matching framework for Integrated Hybrid Resources (IHRs) with grid constraints. An IHR is a collection of Renewable Energy Sources (RES) and flexible customers within a certa…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Flow Matching-Based PET Image Reconstruction

2026-08-20 · Fumio Hashimoto, Ziqian Huang, Tatsuya Yokota, Kuang Gong arxiv

Generative models have shown strong potential for positron emission tomography (PET) image reconstruction. Although diffusion model-based reconstruction methods have demonstrated promising performance, they often require…

Image Reconstruction

Meshy T2: Fast Native Mesh Generation with Flow Matching

2026-07-28 · Jiale Xu, Rendong Liang, Yuhao Long, Siyuan Shen 외 hf

Polygonal meshes are the standard surface representation of modern 3D pipelines, and generating high-quality meshes with artist-style topology is essential for film, gaming, and interactive 3D applications. Mainstream ap…

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

2025-10-13 · Tianyi Tan, Yinan Zheng, Ruiming Liang, Zexu Wang 외 arxiv

Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, re…

Trajectory Modeling Autonomous Driving

Reactive Flux Matching: Mechanism Discovery and Adaptive Sampling of Rare Events

2026-06-04 · Rishal Aggarwal, David Ryan Koes, Nicholas M. Boffi, Eric Vanden-Eijnden arxiv

Path sampling methods generate ensembles of reactive trajectories connecting metastable states, but extracting mechanistic insight from these data remains nontrivial. We introduce Flux Matching, a framework that learns t…