No article text was recorded for this version.
entropy-centric weight representation
Version 1 of 120 papers30 conceptsfrozen 2026-10-04
Papers in this version
- Blog: To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
- Blog: ZipNN: Lossless Compression for AI Models
- Blog: NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
- Blog: 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
- Blog: Compact and Computationally Efficient Representation of Deep Neural Networks
- Blog: NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs
- Blog: GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
- Blog: Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
- Blog: FlashOptim: Optimizers for Memory-Efficient Training
- Blog: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
- Blog: Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask
- Blog: Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference
- Blog: Composite Binary Decomposition Networks
- Blog: Schrödinger's FP: Training Neural Networks with Dynamic Floating-Point Containers
- Blog: Float8@2bits: Entropy Coding Enables Data-Free Model Compression
- Blog: PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
- Blog: Structured Compression by Weight Encryption for Unstructured Pruning and Quantization
- Blog: Reducing the GPU Memory Bottleneck with Lossless Compression for ML
- Blog: A study on speech enhancement using exponent-only floating point quantized neural network (EOFP-QNN)
- Blog: Z ip S erv : Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
History & citation
Current · Permanent link
- This direction split from Exploiting Bit Level Redundancy in Floating Point Weights (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_entropy_centric_weight_representation_1a544416,
title = {entropy-centric weight representation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/entropy-centric-weight-representation/rdr_1a5444166a4d448584a9a86238a3dbd1},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_entropy_centric_weight_representation_1a544416_v1,
title = {entropy-centric weight representation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/entropy-centric-weight-representation/rdr_1a5444166a4d448584a9a86238a3dbd1/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}