arXiv:2608. 12239v1 Announce Type: cross Abstract: Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms.
arXiv:2506.11784v2 Announce Type: replace Abstract: Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-wid...
Squeeze10-LLM is a staged mixed‑precision post‑training quantization framework that reduces 16‑bit LLM weights to an average of 1.6 bits per weight by assigning 80% of weights to 1 bit and 20% to 4 bits. It introduces Post‑Binarization Activation Robustness (PBAR), a weight significance metric that considers activation impact, and Full Information Activation Supervision (FIAS), a strategy that preserves activation information to limit error propagation. Experiments on LLaMA and LLaMA2 demonstrate that Squeeze10‑LLM achieves state‑of‑the‑art performance for sub‑2‑bit weight‑only quantization, raising average accuracy from 43% to 56% on six zero‑shot classification tasks.
arXiv:2605. 25054v2 Announce Type: replace-cross Abstract: Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss.
Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms. Uniform fixed-precision quantization alleviates these issues but suffers severe quality degradation at low bit widths because it ignores differences in the quantization sensitivities of individual layers.
arXiv:2607. 06600v1 Announce Type: cross Abstract: Line segment detection is a key building block in visual SLAM, 3D reconstruction, and industrial inspection.
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
The paper introduces W16A16, a 16‑bit precision quantization method for convolutional neural networks aimed at microcontroller units. On the Armv7E‑M architecture, W16A16 delivers faster inference speeds and lower energy consumption than existing quantization schemes while reducing quantization errors by roughly tenfold compared to 8‑bit approaches. The authors analyze the MCU architecture, explain why 16‑bit operations yield performance gains, and evaluate empirical errors and resource usage across regression and classification tasks.
arXiv:2509. 10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost.
arXiv:2609.28358v1 Announce Type: cross Abstract: Microscaling quantization techniques are increasingly used to represent neural network parameters with 8 bits or fewer while preserving near-full pre...
arXiv:2606. 26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs.
Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these developments, training and deployment of neural network models on embedding and edge devices face significant challenges due to limited memory and computational resources.