SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance

• URL: http://arxiv.org/abs/2606.30113v1
• Date: Mon, 29 Jun 2026 10:45:53 GMT
• Title: SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance
• Abstract summary: We propose SA-VLA, a state-aware action tokenizer that conditions action decoding on robot state.<n>On 12 RoboTwin manipulation tasks, SA-VLA improves the average success rate from 0.29 to 0.56 over the strongest tokenizer baseline.
• Score: 12.586771228417112
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challenging. Existing tokenizers typically map each discrete code to a fixed continuous action prototype, ignoring the robot's current proprioceptive state. This limitation is particularly pronounced in manipulation, where the same action token may require different continuous controls under different joint configurations, object poses, and contact conditions. We therefore propose SA-VLA, a state-aware action tokenizer that conditions action decoding on robot state. We study two state-injection mechanisms for VQ-based action tokenization: cross-attention between state and action features, and a lightweight state adapter that predicts action-wise modulation factors for state-conditioned action modulation and reconstruction. The adapter formulation expands the effective support of a finite codebook by allowing each discrete token to represent a family of state-dependent continuous actions, while preserving the efficiency and compatibility of discrete action modeling. Integrated into an LLM-based VLA policy, SA-VLA supports both autoregressive and parallel action-token decoding with minimal changes to the model interface. On 12 RoboTwin manipulation tasks, SA-VLA improves the average success rate from 0.29 to 0.56 over the strongest tokenizer baseline. In zero-shot sim-to-real experiments on three real-world tasks, it further improves average success from 0.15 to 0.33 over the strongest tokenizer baseline. These results demonstrate that state-conditioned action decoding is a simple and effective mechanism for reducing the compression gap in discrete VLA policies.

Related papers

• Unified Condition-Action Modeling for Accurate One-Step Action Generation [24.554218523494498]
  UCA-Flow is a unified condition-action modeling framework for accurate one-step action generation.<n>Our method unifies observation conditions, timestep conditions, interval conditions, and action tokens into a single sequence, and processes them with a Unified Condition-Action Transformer.
  arXiv  Detail & Related papers  (2026-08-17T06:14:16Z)
• S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation [34.73337776403718]
  Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, but their performance degrades significantly in long-horizon tasks.<n>We propose S$2$-VLA, a framework that introduces a State-Space Guided Adaptive Attention (SSGAA) mechanism.<n>S$2$-VLA consistently outperforms larger 7B-scale models and achieves state-of-the-art performance on long-horizon manipulation benchmarks.
  arXiv  Detail & Related papers  (2026-06-26T09:13:16Z)
• RotVLA: Rotational Latent Action for Vision-Language-Action Model [54.22746299071677]
  We introduce RotVLA, a VLA framework built on a continuous rotational latent action representation.<n>Latent actions are modeled as elements of SO(n), providing continuity, compositionality, and structured geometry aligned with real-world action dynamics.<n>RotVLA consists of a VLM backbone and a flow-matching action head, pretrained on large-scale cross-embodiment robotic datasets and human videos.
  arXiv  Detail & Related papers  (2026-05-13T11:58:02Z)
• LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models [13.30873593845724]
  LoopVLA is a recurrent Vision-Language-Action architecture that learns representation refinement, action prediction, and sufficiency estimation.<n>We show that LoopVLA pushes the efficiency-performance frontier of VLA policies, reducing parameters by 45% and improving inference throughput by up to 1.7 times.
  arXiv  Detail & Related papers  (2026-05-11T03:51:22Z)
• DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching [20.252867273996085]
  We propose DFM-VLA, a discrete flow matching VLA for iterative refinement of action tokens.<n>DFM-VLA consistently outperforms strong autoregressive, discrete diffusion, and continuous diffusion baselines in manipulation performance.
  arXiv  Detail & Related papers  (2026-03-27T11:38:43Z)
• See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation [59.07792608884117]
  We introduce See, Plan, Rewind (SPR), a progress-aware vision-language-action framework.<n>SPR operates through a continuous core cycle, Seeing the current state and upcoming milestone, Planning a trajectory towards the next 2D waypoint, and Rewinding to a recoverable state upon failure.<n>SPR achieves state-of-the-art robustness with the smallest performance drop, surpassing OpenVLA-OFT and UniVLA.
  arXiv  Detail & Related papers  (2026-03-10T07:22:51Z)
• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation [21.23747444669735]
  We propose Action-Context-aware Adaptive Computation for VLA models (AC2-VLA)<n>AC2-VLA adaptively performs cognition reuse across timesteps, token pruning, and selective execution of model components within a unified mechanism.<n>Experiments on robotic manipulation benchmarks show that AC2-VLA achieves up to a 1.79times speedup while reducing FLOPs to 29.4% of the dense baseline.
  arXiv  Detail & Related papers  (2026-01-27T14:10:39Z)
• FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization [61.10456021136654]
  We introduce FASTer, a unified framework for efficient and general robot learning.<n>FASTerVQ encodes action chunks as single-channel images, capturing global-temporal dependencies while maintaining a high compression ratio.<n>FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance.
  arXiv  Detail & Related papers  (2025-12-04T16:21:38Z)
• $\mathcal{E}_0$: Enhancing Generalization and Fine-Grained Control in VLA Models via Continuized Discrete Diffusion [65.77755100137728]
  We introduce E0, a continuized discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens.<n>E0 achieves state-of-the-art performance across 14 diverse environments, outperforming strong baselines by 10.7% on average.
  arXiv  Detail & Related papers  (2025-11-26T16:14:20Z)
• SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation [65.6201974979119]
  We propose SemanticVLA, a novel VLA framework that performs Semantic-Hierarchical Sparsification and Enhancement for Efficient Robotic Manipulation.<n>SemanticVLA surpasses OpenVLA on LIBERO benchmark by 21.1% in success rate, while reducing training cost and inference latency by 3.0-fold and 2.7-fold.
  arXiv  Detail & Related papers  (2025-11-13T17:24:37Z)
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [70.72227437717467]
  Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
  arXiv  Detail & Related papers  (2025-06-15T05:04:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.