mlsanityData to 14 Oct 2026

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models

arXiv 2505.21567 ↗First posted 27 May 2025cs.CV cs.LGcited by 3

On the map: Vision-language-action models → Efficient VLA inference and adaptation

Abstract (arXiv)

With the development of Embodied Artificial intelligence, the end-to-end control policy such as Vision-Language-Action (VLA) model has become the mainstream. Existing VLA models faces expensive computing/storage cost, which need to be optimized. Quantization is considered as the most effective method which can not only reduce the memory cost but also achieve computation acceleration. However, we find the token alignment of VLA models hinders the application of existing quantization methods. To address this, we proposed an optimized framework called EaqVLA, which apply encoding-aligned quantization to VLA models. Specifically, we propose an complete analysis method to find the misalignment in various granularity. Based on the analysis results, we propose a mixed precision quantization with the awareness of encoding alignment. Experiments shows that the porposed EaqVLA achieves better quantization performance (with the minimal quantization loss for end-to-end action control and xxx times acceleration) than existing quantization methods.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 6 of its 9 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

6 of 9 references.

References · 6

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  6. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantizationcited by 28
  2. 2026Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Modelscited by 2
  3. 2026When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variantscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
  2. 2025SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
  3. 2026QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
  4. 2026HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
  5. 2026VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models
  6. 2026HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
  7. 2026DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
  8. 2026A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference