Hyper-Efficient Quantized Neural Network Pruning via Adaptive Bit-Width Allocation
dev.to·1d·
Discuss: DEV
📊Quantization
An Interview with Julio Barba
halide.cx·18h·
Discuss: Lobsters, Hacker News
🎬AV1 Encoding
Guide to Contrastive Learning: Techniques, Models, and Applications
medium.com·11h·
Discuss: Hacker News
🧠Machine Learning
Unlocking Multimodal Video Transcription with Gemini
towardsdatascience.com·1d
✅Verification Codecs
Symmetry in subword segmentation
languagelog.ldc.upenn.edu·2h
📄Text Segmentation
First Indeo codecs
codecs.multimedia.cx·14h
🎬Video Codecs
CORE: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning
arxiv.org·2d
⚙️Compression Benchmarking
When your camera’s zoom is an AI illustration ↦
sixcolors.com·1d
🤖Advanced OCR
Optical generative models
nature.com·3d
🌈Holographic Archives
Why “AI” instead of “LLM”
brajeshwar.com·1h
💻Local LLMs
From Multi-Head to Latent Attention: The Evolution of Attention Mechanisms
vinithavn.medium.com·19h·
Discuss: Hacker News
⧗Information Bottleneck
A 20-Year-Old Algorithm Can Help Us Understand Transformer Embeddings
ai.stanford.edu·3d·
Discuss: Hacker News
🧮Vector Embeddings
Kids as Philosophers of AI
turingpost.com·9h·
Discuss: Hacker News
🔲Cellular Automata
Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition
arxiv.org·2d
🎧Learned Audio
Show HN: VO3 – AI video generator powered by Google Veo 3
vo3.art·1d·
Discuss: Hacker News
🧠Learned Codecs
Compress Vectors by 4x by using 8-bit Rotational Quantization
weaviate.io·2d·
Discuss: Hacker News
📊Vector Quantization
Whisper it: FFmpeg 8 can now subtitle your videos on the fly
theregister.com·2d
🎬AV1 Encoding
The Art of Transformer Programming (2023)
yanivle.github.io·2h·
Discuss: Hacker News
🤖Lisp Machines
ByteDance releases OmniHuman-1.5: long-form, emotion-aware AI avatars
omnihuman-lab.github.io·3d·
Discuss: Hacker News
🧠Learned Codecs
Bootstrapping a Forth for Art
tia.mat.br·2h·
Discuss: Lobsters, Hacker News
🔗Concatenative Programming