Data Compression with Relative Entropy Coding
arxiv.org·2d
📐Compression Mathematics
SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
arxiv.org·1d
⚡Modern Compression
Google/Videoprism
huggingface.co·15h·
Discuss: Hacker News
📊Learned Metrics
Deep-OFDM: Neural Modulation for High Mobility
arxiv.org·1d
🧠Neural Codecs
Why Your Next LLM Might Not Have A Tokenizer
towardsdatascience.com·18h
🤖Grammar Induction
Video Compression for Spatiotemporal Earth System Data
arxiv.org·10h
📊Rate-Distortion Theory
The Art of Deception: Understanding Generative Adversarial Networks (GANs)
dev.to·11h·
Discuss: DEV
🧠Neural Codecs
Code Rate Optimization via Neural Polar Decoders
arxiv.org·2d
🧠Neural Codecs
LVPNet: A Latent-variable-based Prediction-driven End-to-end Framework for Lossless Compression of Medical Images
arxiv.org·1d
🧠Learned Compression
Kernel Limit of Recurrent Neural Networks Trained on Ergodic Data Sequences
arxiv.org·1d
🧠Neural Codecs
MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
arxiv.org·1d
🧠Neural Codecs
A Simple but Accurate Approximation for Multivariate Gaussian Rate-Distortion Function and Its Application in Maximal Coding Rate Reduction
arxiv.org·1d
🧠Learned Compression
Greedy Is Good. Less Greedy May Be Better
gojiberries.io·13h·
Discuss: Hacker News
🧮Kolmogorov Complexity
The first CNN for playing Scrabble – a game of imperfect information
cesardelsolar.com·2d·
Discuss: Hacker News
🔲Cellular Automata
Fast Rate Information-theoretic Bounds on Generalization Errors
arxiv.org·1d
⧗Information Bottleneck
Portable Network Graphics (PNG) Specification (Third Edition)
w3.org·17h·
Discuss: Hacker News
🕸️WebP Analysis
Plan for Speed -- Dilated Scheduling for Masked Diffusion Language Models
arxiv.org·10h
💻Local LLMs
Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
arxiv.org·10h
📊Learned Metrics
UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
arxiv.org·1d
🗜️LZW Variants
Towards Deeper GCNs: Alleviating Over-smoothing via Iterative Training and Fine-tuning
arxiv.org·1d
📊Learned Metrics