arXiv AI
FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 21
HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
arXiv:2602. 13710v2 Announce Type: replace Abstract: 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.
arXiv AI
Jun 8
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
arXiv:2605. 24011v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical.
arXiv Machine Learning
Aug 10
{\Omega}-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling
arXiv:2605. 28803v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
arXiv Machine Learning
Aug 12
HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
arXiv:2605. 28803v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
arXiv AI
Aug 18
Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification
arXiv:2608. 15636v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hinder real-time deployment.
arXiv Machine Learning
Jul 31
QuantWAMs: Calibrating at the Right Granularity for World Action Models
arXiv:2607. 28405v1 Announce Type: cross Abstract: World Action Models (WAMs) jointly predict future observations and actions, but their iterative denoising and closed-loop execution make efficient deployment costly.