conftrace_

low bit-width

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model compression (5) quantization training (2) low-bit representation (2) weight quantization (2) model quantization (2) post-training quantization (2) neural network quantization (2) neural network (1) transformer quantization (1) channel-wise scaling (1)

Papers

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization ICCV 2025 IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers ICML 2024 Understanding and Overcoming the Challenges of Efficient Transformer Quantization EMNLP 2021 Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks IJCAI 2020 Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations AAAI 2020 Fully Quantized Network for Object Detection CVPR 2019