Adaptive Quantization-Aware Pruning for Efficient Federated Learning of Edge AI Models
dev.to·9h·
Discuss: DEV
📊Quantization
Video Compression Basics
rastergrid.com·12h·
Discuss: Hacker News
🎬AV1 Encoding
Hilbert space: treating functions as vectors
eli.thegreenplace.net·19h
📐Linear Algebra
EmbeddingGemma Model Card
ai.google.dev·5h·
Discuss: Hacker News
⚙️Compression Benchmarking
Covariant spatio-temporal receptive fields for spiking neural networks
nature.com·7h·
Discuss: Hacker News
🌀Hyperbolic Geometry
Clustering
dev.to·16h·
Discuss: DEV
📚Document Clustering
A Gentle Introduction to Batch Normalization
machinelearningmastery.com·1d
🧠Neural Compression
Technology reveals the stories erased from ancient manuscripts
english.elpais.com·1d
📜Palimpsest Analysis
ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction
arxiv.org·2d
🏺Compression Museums
Dream: Visual Decoding from Reversing Human Visual System
github.com·4h·
Discuss: Hacker News
🧠Neural Codecs
FlashAttention by hand
dev.to·19h·
Discuss: DEV
⚡SIMD Vectorization
ML Systems: Motivating Dense Models
jacobkahn.me·3d·
Discuss: Hacker News
🧠Machine Learning
How to train your Dragon^H^H AI overlord
virtuallyfun.com·20h
🧲RISC-V Archaeology
Parallelization Strategies in Neural Networks
nwktimes.blogspot.com·1d·
Discuss: Hacker News
🌊Streaming Algorithms
Unlocking Hidden Order: Differentiable Entropy as a Code Optimizer
dev.to·1d·
Discuss: DEV
🧠Machine Learning
Automated Anomaly Detection in 3D Confocal Microscopy Stacks via Hyperdimensional Vector Analysis
dev.to·22h·
Discuss: DEV
🚀SIMD Text Processing
LLMs from Scratch Using Middle School Math – TDS Archive
medium.com·2d·
Discuss: Hacker News
📊Quantization
Binary Quantization For LLMs Through Dynamic Grouping
arxiv.org·3d
💻Local LLMs
Zero-Inflated Data: A Comparison of Regression Models
towardsdatascience.com·1d
🎯Arithmetic Coding Theory
I Was Wrong: Start Simple, Then Move to More Complex
charles-frenzel.medium.com·2d·
Discuss: Hacker News
🗂️Vector Databases