FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding

arXiv:2609.24433 · cs.RO, cs.AI, cs.SY, eess.SY · Submitted 2026-09-21 · Read on arXiv

cs.RO, cs.AI, cs.SY, eess.SY

Submitted: 2026-09-21

Updated: 2026-09-21

Comments: 8 pages, 5 figures, 7 tables. Code: https://github.com/cair-vinuni/FoldQuantVLA

Code: https://github.com/cair-vinuni/FoldQuantVLA

Project page: https://review-artifact-27f4.github.io/foldquantvla

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Quantization — 36× in this paper · explained in 12 episodes
• Calibration — 24× in this paper · explained in 7 episodes
• Fidelity — 13× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Action Decoder — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Topological Order — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs
• ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
• DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
• HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
• AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
• Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
• HadaCore: Tensor Core Accelerated Hadamard Transform Kernel
• BitNet a4.8: 4-bit Activations for 1-bit LLMs
• Evaluating Real-World Robot Manipulation Policies in Simulation
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving