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

arXiv:2609.22854 · cs.RO, cs.CV · Submitted 2026-09-19 · Read on arXiv

cs.RO, cs.CV

Submitted: 2026-09-19

Updated: 2026-09-19

Terminology

• Benchmark — 16× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Anisotropy — 4× in this paper · explained in 3 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Flow Matching — 3× in this paper · explained in 7 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Object Occlusion — 2× in this paper
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Object Motion — 1× in this paper
• Object Relations — 1× in this paper
• Object Sequence — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• VLA Models — 1× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• $\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
• 2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• X-IL: Exploring the Design Space of Imitation Learning Policies
• ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries
• SmolVLM: Redefining small and efficient multimodal models

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving