SOURCE-LINKED INTELLIGENCE

M2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Recent advancements have successfully adapted autoregressive language models to process multimodal signals, such as images and actions. Since raw action signals are continuous, effective tokenization is essential to map high-dimensional inputs into compact discrete tokens for autoregressive processing. However, existing discrete action tokenizers often suffer from high reconstruction loss, failing to preserve the fine-grained dynamics required for precise control. This "discretization bottleneck" significantly limits the performance ceiling of downstream Vision-Language-Action (VLA) models. To

Read original source ↗ Open in workspace

recordType

paper

region

Global