GitHub

paretoq_improving_scaling_laws_in_extremely_low-bit_llm_quantization.md

This paper proposes ParetoQ — the first unified framework supporting 1/1.58/2/3/4-bit quantization — which systematically studies training strategies (full-precision pretraining vs. QAT budget ...
GitHub

APEX -- Adaptive Precision for EXpert Models

Beats Q8_0 perplexity at half the size -- and even beats F16. APEX outperforms Unsloth Dynamic 2.0 (UD) quantizations on perplexity, HellaSwag, and inference speed while being 2x smaller: APEX ...
IEEE

FD-LSCIC: Frequency Decomposition-Based Learned Screen Content Image Compression

Abstract: The learned image compression (LIC) methods have already surpassed traditional techniques in compressing natural scene (NS) images. However, directly applying these methods to screen content ...
Frontiers

Cascaded multiplier-free implementation of adaptive anti-jamming filter based on GNSS receiver

Evaluating the computational complexity is critical for assessing the time-domain anti-jamming performance of GNSS receivers. The multiplier is the core component that contributes to the computational ...
IEEE

An AMBTC Authentication Scheme With Recoverability Using Matrix Encoding and Side Match

Abstract: This paper presents an authentication scheme with recoverability based on Absolute moment block truncation coding (AMBTC). Previous works do not take into account characteristics of the ...