mlsanityData to 14 Oct 2026

Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models

arXiv 2606.19565 ↗First posted 17 Jun 2026cs.CVcited by 2

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

Abstract (arXiv)

We propose Mix-QVLA, a task-evidence-aware mixed-precision PTQ framework for VLA models. Mix-QVLA anchors each quantized variant to the full-precision action-token reference decision and evaluates whether quantization preserves task-relevant evidence across key VLA functional boundaries. It computes normalized gradient-weighted task-evidence maps from boundary activations and compares full-precision and quantized maps using evidence-mass and attribution-distribution distortion, capturing changes in both the strength and allocation of decision-supporting evidence. A soft-bottleneck objective aggregates boundary-level degradation into layer-wise sensitivity scores. Mix-QVLA further models sensitivity throughout task execution, capturing phase-dependent shifts in layer importance rather than assuming a fixed sensitivity profile. The resulting evidence- and time-aware scores guide mixed-precision bit allocation under model-size and BitOps budgets. Extensive evaluations on OpenVLA-style policies show that Mix-QVLA improves the accuracy-efficiency trade-off of low-bit VLA deployment. On LIBERO, Mix-QVLA reduces OpenVLA-OFT memory from 15.4 GB to 4.1 GB, retains 96.3 average success compared with 97.1 for the BF16 model, and achieves a 1.52x inference speedup.

Key facts. Cited by 2 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 26 of its 26 references that are in the map. First posted on arXiv 17 Jun 2026.

Builds on

26 of 26 references.

Closest ancestors · 9

Same direction, newest first

  1. 2026DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models13 Apr
  2. 2026DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models9 Mar
  3. 2026QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models23 Feb
  4. 2026QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization3 Feb
  5. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding16 Jun
  6. 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models11 Jun
  7. 2025EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models27 May
  8. 2025MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation26 Mar
  9. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding4 Mar

Other references · 17

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  4. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  5. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  6. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  7. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  8. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  9. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  10. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  11. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  12. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
5 more
  1. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 641
  2. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  3. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 424
  4. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 410
  5. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Modelscited by 0
  2. 2026ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inferencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models
  2. 2026HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
  3. 2025SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
  4. 2026CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation
  5. 2026HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
  6. 2026CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
  7. 2025MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective
  8. 2026ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models