Skip to content
conftrace_

bit-width reduction

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model compression (4) model quantization (3) weight quantization (2) large language model (2) straight-through estimator (2) neural network optimization (2) parameter quantization (1) mixed-precision quantization (1) low-bit quantization (1) parameter initialization (1)

Papers

OneBit: Towards Extremely Low-bit Large Language Models NeurIPS 2024 PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression NeurIPS 2024 A Mixed-Precision Quantization Method without Accuracy Degradation Using Semilayers ACML 2023 Network Quantization With Element-Wise Gradient Scaling CVPR 2021 Adaptive Loss-Aware Quantization for Multi-Bit Networks CVPR 2020 Towards Effective Low-Bitwidth Convolutional Neural Networks CVPR 2018