SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Low-bit vision-language-action inference must reduce observation-to-action latency while preserving robot behavior. We present FoldQuantVLA, a post-training quantization framework that carries a consistent activation representation through calibration, weight rounding, and native integer execution. It combines channel scaling and block Hadamard transforms with dynamic per-token quantization, without policy retraining. Custom TensorRT plugins execute projections in both the language backbone and iterative action expert with four-bit weights and activations (W4A4) on Ada GPUs and Jetson AGX Orin

Read original source ↗ Open in workspace

recordType

paper

region

Global