SOM-VQ: Topology-Aware Tokenization for Interactive Generative Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Londei, Alessandro, Lanzieri, Denise, Benati, Matteo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917292788416512
author Londei, Alessandro
Lanzieri, Denise
Benati, Matteo
author_facet Londei, Alessandro
Lanzieri, Denise
Benati, Matteo
contents Vector-quantized representations enable powerful discrete generative models but lack semantic structure in token space, limiting interpretable human control. We introduce SOM-VQ, a tokenization method that combines vector quantization with Self-Organizing Maps to learn discrete codebooks with explicit low-dimensional topology. Unlike standard VQ-VAE, SOM-VQ uses topology-aware updates that preserve neighborhood structure: nearby tokens on a learned grid correspond to semantically similar states, enabling direct geometric manipulation of the latent space. We demonstrate that SOM-VQ produces more learnable token sequences in the evaluated domains while providing an explicit navigable geometry in code space. Critically, the topological organization enables intuitive human-in-the-loop control: users can steer generation by manipulating distances in token space, achieving semantic alignment without frame-level constraints. We focus on human motion generation - a domain where kinematic structure, smooth temporal continuity, and interactive use cases (choreography, rehabilitation, HCI) make topology-aware control especially natural - demonstrating controlled divergence and convergence from reference sequences through simple grid-based sampling. SOM-VQ provides a general framework for interpretable discrete representations applicable to music, gesture, and other interactive generative domains.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21133
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SOM-VQ: Topology-Aware Tokenization for Interactive Generative Models
Londei, Alessandro
Lanzieri, Denise
Benati, Matteo
Machine Learning
Vector-quantized representations enable powerful discrete generative models but lack semantic structure in token space, limiting interpretable human control. We introduce SOM-VQ, a tokenization method that combines vector quantization with Self-Organizing Maps to learn discrete codebooks with explicit low-dimensional topology. Unlike standard VQ-VAE, SOM-VQ uses topology-aware updates that preserve neighborhood structure: nearby tokens on a learned grid correspond to semantically similar states, enabling direct geometric manipulation of the latent space. We demonstrate that SOM-VQ produces more learnable token sequences in the evaluated domains while providing an explicit navigable geometry in code space. Critically, the topological organization enables intuitive human-in-the-loop control: users can steer generation by manipulating distances in token space, achieving semantic alignment without frame-level constraints. We focus on human motion generation - a domain where kinematic structure, smooth temporal continuity, and interactive use cases (choreography, rehabilitation, HCI) make topology-aware control especially natural - demonstrating controlled divergence and convergence from reference sequences through simple grid-based sampling. SOM-VQ provides a general framework for interpretable discrete representations applicable to music, gesture, and other interactive generative domains.
title SOM-VQ: Topology-Aware Tokenization for Interactive Generative Models
topic Machine Learning
url https://arxiv.org/abs/2602.21133