diff --git a/_publications/gavrilov2026inspectable.markdown b/_publications/gavrilov2026inspectable.markdown
new file mode 100644
index 00000000..334e5857
--- /dev/null
+++ b/_publications/gavrilov2026inspectable.markdown
@@ -0,0 +1,12 @@
+---
+layout: publication
+title: "Inspectable Control for Structure-Preserving Software Regeneration"
+authors: Alexey Gavrilov, Alan-Barsag Gazzaev, Mikhail Mozikov, Ilya Makarov, Sergey Muravyov
+conference: FSE Companion
+year: 2026
+additional_links:
+  - {name: "DOI", url: "https://doi.org/10.1145/3803437.3807386"}
+  - {name: "website", url: "https://aogavrilov.com/publications/inspectable-control/"}
+tags: ["code generation", "representation"]
+---
+Software-engineering workflows such as constrained repair, staged refinement, and structure-preserving modification require control over what changes and what remains fixed. Token-level generation is a weak control surface for these operations because it constrains local surface text rather than the coarse structural invariants that software engineering often aims to preserve. We study hierarchical discrete latents as an inspectable intermediate representation for software artifacts: a hierarchical VQ-VAE compresses a 64-token Python function into coarse and fine discrete codes, and masked discrete generation regenerates only selected positions under partial constraints. On 2,000 preprocessed Python functions, locking four top-level codes improves parse rate from 0.453 to 0.591 while preserving substantial change in unlocked positions (edit freedom, 0.936) and near-maximal sample uniqueness (diversity, 0.998). Under fixed coarse context, lower-level refinement is weaker but remains monotonic, supporting a coarse-to-fine reading of the hierarchy. Overall, these results provide early evidence for a practical control layer that supports bounded, structure-preserving software-artifact regeneration above the token level.