Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

TL;DR

OptimusVLA is introduced, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM) that replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories, thereby shortening the generative path and reducing the umber of function evaluations (NFE).

Abstract

Hierarchical Vision-Language-Action (VLA) models have rapidly become a dominant paradigm for robotic manipulation. It typically comprising a Vision-Language backbone for perception and understanding, together with a generative policy for action generation. However, its performance is increasingly bottlenecked by the action generation proceess. (i) Low inference efficiency. A pronounced distributional gap between isotropic noise priors and target action distributions, which increases denoising steps and the incidence of infeasible samples. (ii) Poor robustness. Existing policies condition solely on the current observation, neglecting the constraint of history sequence and thus lacking awareness of task progress and temporal consistency. To address these issues, we introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM). GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories, thereby shortening the generative path and reducing the umber of function evaluations (NFE). LCM dynamically models executed action sequence to infer task progress and injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory. Across three simulation benchmarks, OptimusVLA consistently outperforms strong baselines: it achieves 98.6% average success rate on LIBERO, improves over pi_0 by 13.5% on CALVIN, and attains 38% average success rate on RoboTwin 2.0 Hard. In Real-World evaluation, OptimusVLA ranks best on Generalization and Long-horizon suites, surpassing pi_0 by 42.9% and 52.4%, respectively, while delivering 2.9x inference speedup.

Figures (8)

• Figure 1: Top: Comparison between the standard VLA architecture (left) and our proposed OptimusVLA (right). (ii) Poor robustness to temporal dependence. Middle: Illustration of how GPM (blue) and LCM (green) address two key limitations of existing VLA models: (i) Low inference efficiency due to a large prior–target gap. (ii) Poor robustness to temporal dependence. Bottom: Efficiency and performance comparison.
• Figure 2: Overview of OptimusVLA framework. Given a task and the current observation, the Vision–Language backbone first encodes the inputs into a multimodal representation. GPM then retrieves a task-level prior based on this representation, while LBM dynamically encodes the historical action sequence to produce a consistency constraint. Finally, the flow policy denoises the initialization with an adaptive NFEs schedule to generate the action chunk.
• Figure 3: Real-world task setup and evaluation results. We evaluate the performance of OptimusVLA against OpenVLA kim2024openvla, OpenVLA-OFT kim2025openvla-oft, $\pi_{0}$black2024pi0, and $\pi_{0.5}$intelligence2025pi05 on the Generalization Tasks and Long-horizon Tasks suites.
• Figure 4: Training efficiency comparison between OptimusVLA and $\pi_{0.5}$intelligence2025pi05. Initialized from same weights, OptimusVLA attains strong performance with substantially fewer training steps.
• Figure 5: Inference efficiency comparison on LIBERO and Real-World. OptimusVLA attains strong performance with substantially fewer inference time and NFEs.