SOURCE-LINKED INTELLIGENCE

SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Edge vision models are difficult to deploy on resource-constrained hardware, making low-bit post-training quantization (PTQ) attractive. In practice, standard FP32 training often produces heavy-tailed activation distributions whose outliers destabilize activation quantization: preserving the full range wastes quantization bins on rare extremes, while aggressive clipping causes information loss. Existing solutions typically rely on quantization-aware training (QAT), which adds training complexity and bit-width coupling, or advanced PTQ procedures that repair the model after training. We present

Read original source ↗ Open in workspace

recordType

paper

region

Global