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

• URL: http://arxiv.org/abs/2606.19565v1
• Date: Wed, 17 Jun 2026 20:08:14 GMT
• Title: Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
• Abstract summary: Mix-QVLA is a task-evidence-aware mixed-precision PTQ framework for VLA models.<n>It computes normalized gradient-weighted task-evidence maps from boundary activations.<n>It captures changes in both the strength and allocation of decision-supporting evidence.
• Score: 2.1485350418225244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• QuantWAMs: Calibrating at the Right Granularity for World Action Models [34.540026172139406]
  World Action Models jointly predict future observations and actions, but their iterative denoising and closed-loop execution make deployment costly.<n>We present QuantWAMs, a PTQ framework that aligns quantization decisions with the calibration context defined by model structure, rollout distribution, and task objective.<n>We evaluate QuantWAMs on Fast-WAM and LingBot-VA across RoboTwin 2.0, LIBERO, and real-robot manipulation with an AgiBot G2.
  arXiv  Detail & Related papers  (2026-07-30T15:54:29Z)
• Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models [60.17417174639865]
  Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining.<n>The prevailing remedy, post-training, improves task-specific performance but narrows the generalist capability that makes pretraining valuable.<n>We propose SVA, a framework that equips frozen VLA policies with long-term consequence awareness.
  arXiv  Detail & Related papers  (2026-07-04T07:53:10Z)
• MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization [14.071776510862824]
  This work proposes MGVQ, a novel vector quantization framework integrating multi-dimensional sensitivity perception and gradient-Hessian fusion.<n>In 2-bit quantization settings, MGVQ surpasses existing advanced post-training quantization methods significantly, achieving a maximum accuracy improvement of 4.9 points.<n>The proposed method realizes stable and efficient ultra-low-bit VLM quantization, greatly promoting the practical deployment of multimodal large models in resource-limited environments.
  arXiv  Detail & Related papers  (2026-05-20T06:11:25Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization [29.21308068128823]
  We introduce QVLA, the first action-centric quantization framework specifically designed for embodied control.<n>Our work establishes a new, principled foundation for compressing Vision-Language-Action models in robotics.
  arXiv  Detail & Related papers  (2026-02-03T17:43:45Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering [52.69447404069251]
  Large vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning.<n>We propose Prune-Then-Plan, a framework that stabilizes exploration through step-level calibration.
  arXiv  Detail & Related papers  (2025-11-24T22:50:50Z)
• MoPEQ: Mixture of Mixed Precision Quantized Experts [0.1262792599323502]
  Mixed Precision Quantization assigns different precisions to different layers of an LLM/VLM based on layer sensitivity and importance within the model.<n>We propose a Post Training Quantization algorithm, MoPEQ, that assigns optimal bit width to each expert.<n>Our method balances accuracy and model size by analyzing each expert's sensitivity using Hessian trace approximation.
  arXiv  Detail & Related papers  (2025-09-02T17:04:59Z)
• EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models [10.58181401714169]
  We propose an optimized framework called EaqVLA, which apply encoding-aligned quantization to VLA models.<n>EaqVLA achieves better quantization performance (with the minimal quantization loss for end-to-end action control and xxx times acceleration) than existing quantization methods.
  arXiv  Detail & Related papers  (2025-05-27T05:42:21Z)
• Post-hoc Probabilistic Vision-Language Models [54.05237186168399]
  Vision-language models (VLMs) have found remarkable success in classification, retrieval, and generative tasks.<n>We propose post-hoc uncertainty estimation in VLMs that does not require additional training.<n>Our results show promise for safety-critical applications of large-scale models.
  arXiv  Detail & Related papers  (2024-12-08T18:16:13Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [63.118592279833656]
  Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs)<n>We propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise.<n> Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)

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.