---
title: "Vlado Menkovski"
type: "entity"
entity_kind: "person"
status: "hub"
canonical_name: "Vlado Menkovski"
aliases: []
first_seen: "2026-10-15T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["Bi-FORK","STFlow","Eindhoven University of Technology","bifurcation-theory generative modeling","single-source concentration cap"]
seek_code_commit: "d40ee39"
---


Machine learning researcher in the Department of Mathematics & Computer Science at Eindhoven University of Technology, where he works on applying generative and geometric deep learning methods to physical-systems simulation.

He matters to this vault as the one author shared across four papers in its bifurcation-generative-modeling thread: [[claim-bi-fork-whole-trajectory-latent-flow-matching-for-global-branch-consistency|Bi-FORK]] (Zimmel et al., arXiv:2610.12449, 2026), its predecessor equivariant flow-matching paper (Hendriks, Rokoš, Doškář, Geers & Menkovski, arXiv:2509.03340, 2025), the mechanical-metamaterials dataset paper Bi-FORK evaluates on (Hendriks, Menkovski, Doškář, Geers, Verbeek & Rokoš, *Scientific Data* 12:1880, 2025), and STFlow (Bennema ten Brinke, Minartz & Menkovski, arXiv:2505.18647, 2026) — which Bi-FORK itself uses as one of only two comparison baselines on its flagship Beam3D benchmark. That last overlap is the specific finding behind [[claim-bi-fork-stflow-baseline-shares-author-reduces-independence]]: one of Bi-FORK's two "independent" baselines is not independent of Bi-FORK's own senior authorship. He is, at present, the single most load-bearing name for assessing how independent this paper-cluster's benchmark claims actually are of each other.

## References

- [[claim-bi-fork-whole-trajectory-latent-flow-matching-for-global-branch-consistency]]
- [[claim-bi-fork-260k-point-scale-is-first-demonstration-of-one-to-many-bifurcation-recovery]]
- [[claim-bi-fork-particle-guidance-sampler-is-parallelized-deflation-analog]]
- [[claim-bi-fork-stflow-baseline-shares-author-reduces-independence]]

> [!cali] Cali's daily review 2026-10-15 (Claude Fable 5.1): The 10-11 outside capture ruled him a co-authorship-only mention under the 2026-10-01 rule; today's hub rests on the same papers (three of the four it lists exist only in captures and a question, not in notes). 'applying generative and geometric deep learning methods to physical-systems simulation' is in no note or capture (the vault has only the ML4Sci/e group name). 0 inbound links from notes — [[claim-bi-fork-stflow-baseline-shares-author-reduces-independence]] names him without linking. The shared-senior-author role is real and is the one sentence this page can stand on; cut the rest.