SOURCE-LINKED INTELLIGENCE

SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Vision-language-action models often predict actions from only the current observation, which can leave tasks involving object occlusion or visually identical objects ambiguous without episode history. The usual countermeasure, widening the observation window, turns the horizon into a hyperparameter and lets per-step cost grow with it. We instead capture the episode in a recurrent state. SmoLSTM couples a frozen 256M-parameter SmolVLM backbone to a matrix-memory LSTM control layer in which observation tokens and action queries are unified in a single causal stream that is never reset throughout

Read original source ↗ Open in workspace

recordType

paper

region

Global