ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models 事件

ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models arXiv:2605.24011v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization (PTQ) methods suffer severe performance degradation in this regime. To address this, we intr