No article text was recorded for this version.
asymmetric activation quantization
Version 1 of 136 papers70 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Q-YOLO: Efficient Inference for Real-time Object Detection
- Blog: PTQ4ViT: Post-training Quantization for Vision Transformers with Twin Uniform Quantization
- Blog: LSQ+: Improving low-bit quantization through learnable offsets and better initialization
- Blog: ADFQ-ViT: Activation-Distribution-Friendly post-training Quantization for Vision Transformers
- Blog: 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
- Blog: AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive Mixed-Precision Post-Training Quantization
- Blog: Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
- Blog: PTQ4ViT: Post-training Quantization for Vision Transformers with Twin Uniform Quantization
- Blog: TernaryBERT: Distillation-aware Ultra-low Bit BERT
- Blog: 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
- Blog: QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning
- Blog: Improving Accuracy of Binary Neural Networks Using Unbalanced Activation Distribution
- Blog: PTQ4RIS: Post-Training Quantization for Referring Image Segmentation
- Blog: Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence
- Blog: Designing strong baselines for ternary neural network quantization through support and mass equalization
- Blog: Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
- Blog: PROFIT: A Novel Training Method for sub-4-bit MobileNet Models
- Blog: SpinQuant: LLM quantization with learned rotations
- Blog: Bayesian Network Classifiers with Reduced Precision Parameters
- Blog: KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- Blog: AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model
- Blog: LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
- Blog: Toward Accurate Post-Training Quantization for Image Super Resolution
- Blog: TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
- Blog: Bag of Tricks with Quantized Convolutional Neural Networks for image classification
- Blog: Generalized Batch Normalization: Towards Accelerating Deep Neural Networks
- Blog: PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
- Blog: APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
- Blog: FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
- Blog: PTQ4SAM: Post-Training Quantization for Segment Anything
- Blog: How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training
- Blog: SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision
- Blog: A Simple Low-Bit Quantization Framework for Video Snapshot Compressive Imaging
- Blog: Exploring Post-Training Quantization of Protein Language Models
- Blog: AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference
- Blog: AdaLog: Post-training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
History & citation
Current · Permanent link
- This direction split from Asymmetric Quantization for Skewed Neural Distributions (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_asymmetric_activation_quantization_674f1f67,
title = {asymmetric activation quantization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asymmetric-activation-quantization/rdr_674f1f67bd3e47e68bb64de98fe3addb},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_asymmetric_activation_quantization_674f1f67_v1,
title = {asymmetric activation quantization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asymmetric-activation-quantization/rdr_674f1f67bd3e47e68bb64de98fe3addb/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}