Show HN: Novel GPT-2 sampling and memory architecture
github.com·8h·
Discuss: Hacker News
💎Information Crystallography
Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising
arxiv.org·1d
🧠Neural Codecs
A quick glance at another bunch of codecs
codecs.multimedia.cx·1h
🎬Cinema Codecs
Fully Configurable Open Source Audio Spectrum Analyzer
hackster.io·3h
💿FLAC Archaeology
Dissonance: A journey through musical possibility space
aatishb.com·2h·
Discuss: Hacker News
🌈Spectral Audio
These Popular Noise-Canceling Headphones Are at Their Lowest Price Ever
lifehacker.com·2d
👁️Perceptual Coding
Deep Dive: OpenAI's GPT-OSS
dev.to·14h·
Discuss: DEV
📊Quantization
FFmpeg 8.0 Released
ffmpeg.org·14h·
Discuss: Hacker News
🎬AV1 Encoding
Show HN: A short story on developing a long-context World-Model with no money
francesco215.github.io·23h·
Discuss: Hacker News
🧠Learned Codecs
BenQ has released a pro 4K monitor that has something no rival offers: a 2.1 sound system with a small but useful woofer
techradar.com·2h
🎧Vorbis Encoding
Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent
arxiv.org·1d
🧠Neural Compression
A universal rhythm guides how we speak: Global analysis reveals 1.6-second 'intonation units'
phys.org·2d
🗣️CMU Pronouncing
Shotcut is a free and open-source video editor, available for all major platforms
techspot.com·21h
🎬Video Codecs
Denoising by neural network for muzzle blast detection
arxiv.org·1d
🌊Digital Signal Processing
Cracking the Density Code: Why MAF Flows Where KDE Stalls
towardsdatascience.com·1d
🔗Tailscale
An inner-speech decoder reveals some mental privacy issues
arstechnica.com·6h·
Discuss: Hacker News
🎧Learned Audio
Apple trained a large language model to efficiently understand long-form video
9to5mac.com·19h·
Discuss: Hacker News
🎧Learned Audio
Spiral-Bench shows which AI models most strongly reinforce users' delusional thinking
the-decoder.com·7h
🧠Intelligence Compression
Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
arxiv.org·1d
🧠Intelligence Compression
BioSonix: Can Physics-Based Sonification Perceptualize Tissue Deformations From Tool Interactions?
arxiv.org·2d
🗣️CMU Pronouncing