Skip to content

Similar papers

#machine learning Preprint Oct 2026

Q-PACE: Dynamic Precision Allocation for Quantization-Aware Training

A new approach, called Q-PACE, consisting of a second-order sensitivity model that predicts the loss increase as a sum of quantization noise MSE weighted by per-layer curvature coefficients, and its stability during training allows for infrequent, cheap recalibration.

Alexandra Volkova, Matin Ansaripour, Erik Schultheis et al. · 0 citations
Sep 2026

Adaptive multi-bit progressive quantization for stable training of binary neural networks

This novel progressive quantization framework combines multi-bit assistive teacher models with self-knowledge distillation to stabilize BNN training and integrates matching structured pruning with an asymmetric Binary Weight Network scaling factor, thereby reducing quantization errors while maintaining hardware efficie...

Jie Xu, Wonjun Hwang, Hyunsouk Cho · 0 citations
Book Open access Jul 2026

HAP: Efficient Quantization Harnessing Adaptive Precision for DNN Hardware Acceleration

A novel quantization and accelerator design harnessing adaptive-precision (HAP), leverages a per-group dynamic zero-point to generalize APQ and achieves superior accuracy compared with existing PTQ solutions at the level of 4 or 5 bits for a variety of DNN families.

Er-Jing Luo, Xin-Kuang Geng, Hong-Lan Jiang et al. · 0 citations
Preprint Sep 2026

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

This work presents SCULPT (Statistical Clipping and Uniform Loss for Post-Training), a training-time method that improves PTQ readiness during ordinary FP32 fine-tuning and combines a topology-aware activation regularizer that suppresses quantization-hostile skewness and kurtosis with a stable percentile-based clipping...

Bharadwaj Kavuri, Sourav Babu-PK, Varadhraj Ellapan et al. · 0 citations
#machine learning Preprint Sep 2026

RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models

K-Means clustering is addressed with K-Means clustering, achieving near-lossless accuracy and a mean speed-up over the full-precision model, and it is revealed that excluding from quantization the layers whose speed-up is negligible, regardless of their sensitivity, can be counterproductive.

D. Población-Criado, D. García-Gasulla, Eduardo Quiñones · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.