Compression is prediction | ngrok blog
Compression and LLMs are trying to solve the exact same problem: predicting what comes next. Learn the fundamentals of compression and how better prediction leads to better shrinkage.
compression-encoding
The KV Cache Compression Race: TurboQuant vs OSCAR vs EpiCache - MarkTechPost
Compare TurboQuant, OSCAR, and EpiCache: three 2026 methods compressing the LLM KV cache to cut long-context memory cost
Understanding LLM Distillation Techniques - MarkTechPost
Learn how understanding LLM distillation techniques improves model training through innovative teacher-student approaches.
n this article, we will explore three major approaches used for training one LLM using another:
Hidden Data Science Gem: Rainbow Method for Label Encoding | by Anna Arakel
Make stronger and simpler models by leveraging natural order
Scikit-learn 1.1 Comes with an Improved OneHotEncoder
A simple yet highly practical feature
NSVQ: Improved Vector Quantization technique for Neural Networks Training
Efficient vector quantization for machine learning optimizations (eps. vector quantized variational autoencoders), better than straight…
What is Huffman Coding?
The Huffman Coding algorithm is a building block of many compression algorithms, such as DEFLATE - which is used by the PNG image format and GZIP.
LZ4, an Extremely Fast Compression Algorithm
Comparing Binary, Gray, and One-Hot Encoding
This article shows a comparison of the implementations that result from using binary, Gray, and one-hot encodings to implement state machines in an FPGA. These encodings are often evaluated and applied by the synthesis and implementation tools, so it’s important to know why the…
Beyond One-Hot. 17 Ways of Transforming Categorical Features Into Numeric F
All the encodings that are worth knowing — from OrdinalEncoder to CatBoostEncoder — explained and coded from scratch in Python
Stop One-Hot Encoding Your Categorical Variables.
There are many better alternatives
A Mathematical Primer of Compression
How to reduce storage size without losing information.
BCrypt Explained
Intro If you're into Cryptography For Beginners, you're in the right place. Maybe you're j...
A gentle introduction to Hamming codes
A gentle introduction to Hamming codes, error correcting binary codes whose words are all a Hamming distance of at least 3 apart.
RSA Algorithm
A Self-Contained Tutorial on RSA Algorithm Theories for Number Theory Noobs
What is the Best Audio Codec? — Audiophile ON
Audiophile On lists the best audio codecs for your music if you want the best sound quality, including descriptions of FLAC, OGG, ALAC, DSD, and MQA.
Research Guide: Model Distillation Techniques for Deep Learning
Knowledge distillation is a model compression technique whereby a small network (student) is taught by a larger trained neural network (teacher). The smaller network is trained to behave like the large neural network. This enables the deployment of such models… Continue reading…