[2603.00877] Active Flow Matching

Computer Science > Machine Learning arXiv:2603.00877 (cs) [Submitted on 1 Mar 2026] Title:Active Flow Matching Authors:Yashvir S. Grewal, Daniel M. Steinberg, Thang D. Bui, Cheng Soon Ong, Edwin V. Bonilla View a PDF of the paper titled Active Flow Matching, by Yashvir S. Grewal and 4 other authors View PDF HTML (experimental) Abstract: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. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2603.00877 [cs.LG]   (or arXiv:2603.00877v1 [cs.LG] for this version) ...