mlsanityData to 7 Oct 2026

HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models

arXiv 2602.13710 ↗First posted 14 Feb 2026cs.LGcited by 2

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

Abstract (arXiv)

Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on resource-constrained robots and edge platforms. While reducing weights to 1-bit precision through binarization can greatly improve efficiency, existing methods fail to narrow the distribution gap between binarized and full-precision weights, causing quantization errors to accumulate under long-horizon closed-loop execution and severely degrade actions. To fill this gap, we propose HBVLA, a VLA-tailored binarization framework. First, we use a policy-aware enhanced Hessian to identify weights that are truly critical for action generation. Then, we employ a sparse orthogonal transform for non-salient weights to induce a low-entropy intermediate state. Finally, we quantize both salient and non-salient weights in the Harr domain with group-wise 1-bit quantization. We have evaluated our approach on different VLAs: on LIBERO, quantized OpenVLA-OFT retains 92.2% of full-precision performance; on SimplerEnv, quantized CogAct retains 93.6%, significantly outperforming state-of-the-art binarization methods. We further validate our method on real-world evaluation suite and the results show that HBVLA incurs only marginal success-rate degradation compared to the full-precision model, demonstrating robust deployability under tight hardware constraints. Our work provides a practical foundation for ultra-low-bit quantization of VLAs, enabling more reliable deployment on hardware-limited robotic platforms.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 21 of its 25 references that are in the map. First posted on arXiv 14 Feb 2026.

Builds on

21 of 25 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation9 Jun
  2. 2025Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control21 May

Other references · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  5. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  6. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  7. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  8. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  9. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  10. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  12. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
7 more
  1. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  2. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  3. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  4. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  5. 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMscited by 137
  6. 2022BiT: Robustly Binarized Multi-distilled Transformercited by 51
  7. 2025HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Taskscited by 0
  2. 2026VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
  2. 2026HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
  3. 2026QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
  4. 2026FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding
  5. 2026CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation
  6. 2026ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
  7. 2026DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
  8. 2025EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models