No article text was recorded for this version.
non-uniform weight distribution
Version 2 of 2192 papers218 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
- Blog: Post-Training Piecewise Linear Quantization for Deep Neural Networks
- Blog: AFPQ: Asymmetric Floating Point Quantization for LLMs
- Blog: Non-uniform Step Size Quantization for Accurate Post-training Quantization
- Blog: Pyramid Vector Quantization for LLMs
- Blog: Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
- Blog: Training Ternary Neural Networks with Exact Proximal Operator.
- Blog: AFPQ: Asymmetric Floating Point Quantization for LLMs
- Blog: Tightly-Coupled Data Compression for Efficient Face Alignment
- Blog: Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference
- Blog: UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks
- Blog: Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
- Blog: Meta-Learning Sparse Compression Networks
- Blog: FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization
- Blog: Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models
- Blog: Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
- Blog: Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks
- Blog: Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector
- Blog: Low-bit Quantization Needs Good Distribution
- Blog: Designing strong baselines for ternary neural network quantization through support and mass equalization
- Blog: LogART: Pushing the Limit of Efficient Logarithmic Post-Training Quantization
- Blog: NUPES: Non-Uniform Post-Training Quantization via Power Exponent Search
- Blog: AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
- Blog: FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point
- Blog: Pathology Image Compression with Pre-trained Autoencoders
- Blog: Natural Compression for Distributed Deep Learning
- Blog: A Deep Learning Inference Scheme Based on Pipelined Matrix Multiplication Acceleration Design and Non-uniform Quantization
- Blog: Statistical Model Compression for Small-Footprint Natural Language Understanding
- Blog: Position-based Scaled Gradient for Model Quantization and Sparse Training
- Blog: BitNet Distillation
- Blog: Relaxed Quantization for Discretized Neural Networks
- Blog: FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design
- Blog: KLLM: Fast LLM Inference with K-Means Quantization
- Blog: ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices
- Blog: Improving Low-Precision Network Quantization via Bin Regularization
- Blog: Optimal Gradient Quantization Condition for Communication-Efficient Distributed Training
- Blog: DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
- Blog: Radio: Rate–Distortion Optimization for Large Language Model Compression
- Blog: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
- Blog: BackSlash: Rate Constrained Optimized Training of Large Language Models
- Blog: GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks
- Blog: Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplication
- Blog: An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models
- Blog: Focused Quantization for Sparse CNNs
- Blog: GPTVQ: The Blessing of Dimensionality for LLM Quantization
- Blog: Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
- Blog: MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
- Blog: Low-Precision Mixed-Computation Models for Inference on Edge
- Blog: Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
- Blog: QUIC-FL: Quick Unbiased Compression for Federated Learning
- Blog: Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation
- Blog: CoNLoCNN: Exploiting Correlation and Non-Uniform Quantization for Energy-Efficient Low-precision Deep Convolutional Neural Networks
- Blog: Fully Quantized Image Super-Resolution Networks
- Blog: On Quantizing Implicit Neural Representations
- Blog: PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models
- Blog: Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation
- Blog: Quantization Networks
- Blog: NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
- Blog: Distributive Thermometer: A New Unary Encoding for Weightless Neural Networks
- Blog: EQ-Net: Elastic Quantization Neural Networks
Showing 60 of 192 papers.
History & citation
Current · Permanent link
- distribution-aware quantization split from this direction (53% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_non_uniform_weight_distribution_8719fb3f,
title = {non-uniform weight distribution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-uniform-weight-distribution/rdr_8719fb3f80984023bc0be208779564fd},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_non_uniform_weight_distribution_8719fb3f_v2,
title = {non-uniform weight distribution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-uniform-weight-distribution/rdr_8719fb3f80984023bc0be208779564fd/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}