Data Compression with Relative Entropy Coding
arxiv.org·2d
📐Compression Mathematics
Show HN: Turn Images and Text into AI Videos in Minutes
imagetovideo.io·9h·
Discuss: Hacker News
🎥Streaming Codecs
Fast Rate Information-theoretic Bounds on Generalization Errors
arxiv.org·1d
⧗Information Bottleneck
COPY OF HDMI 2.2's full specs have been finalized, with better support for modern displays
engadget.com·10h
🎬WebCodecs API
Greedy Is Good. Less Greedy May Be Better
gojiberries.io·22h·
Discuss: Hacker News
🧮Kolmogorov Complexity
Video Compression for Spatiotemporal Earth System Data
arxiv.org·19h
📸TIFF Evolution
A large deviation view of \emph{stationarized} fully lifted blirp interpolation
arxiv.org·19h
📐Compression Bounds
Using Wavelets and Clustering to Predict Odd or Even Numbers: An Overengineered Approach with Pretty (But Confusing) Plots
dev.to·10h·
Discuss: DEV
🧠Machine Learning
Benchmarking Video Encoders for LiveKit WebRTC Screen Sharing
gethopp.app·1d·
Discuss: Hacker News
🎥Streaming Codecs
BPCLIP: A Bottom-up Image Quality Assessment from Distortion to Semantics Based on CLIP
arxiv.org·1d
🖼️JPEG XL
Portable Network Graphics (PNG) Specification (Third Edition)
w3.org·1d·
Discuss: Hacker News
🕸️WebP Analysis
InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
arxiv.org·2d
⚡LZ4 Streaming
Fully lifted \emph{blirp} interpolation -- a large deviation view
arxiv.org·19h
🌀Fractal Compression
A Simple but Accurate Approximation for Multivariate Gaussian Rate-Distortion Function and Its Application in Maximal Coding Rate Reduction
arxiv.org·1d
🧠Neural Compression
DRIFT: Data Reduction via Informative Feature Transformation- Generalization Begins Before Deep Learning starts
arxiv.org·19h
🧠Machine Learning
UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
arxiv.org·1d
🗜️LZW Variants
Google/Videoprism
huggingface.co·1d·
Discuss: Hacker News
📊Learned Metrics
Code Rate Optimization via Neural Polar Decoders
arxiv.org·2d
🧠Neural Codecs
Why Your Next LLM Might Not Have A Tokenizer
towardsdatascience.com·1d
🤖Grammar Induction
Plan for Speed -- Dilated Scheduling for Masked Diffusion Language Models
arxiv.org·19h
💻Local LLMs