Exponential Error Bounds for Information Bottleneck Source Coding Problems
arxiv.org·22h
📐Compression Bounds
How JPEG Works: The Subtle Beauty and Art of Imperfection
techspot.com·1d
🖼️JPEG XL
A gentle introduction to Generative AI: Historical perspective
medium.com·1h·
Discuss: Hacker News
🧠Learned Codecs
A small rant about compression
codecs.multimedia.cx·2d
📦Deflate
Explicit Lossless Vertex Expanders!
gilkalai.wordpress.com·16h
💎Information Crystallography
In-Depth Analysis: "Attention Is All You Need"
dev.to·11h·
Discuss: DEV
🧠Intelligence Compression
Detecting and Mitigating Insertion Hallucination in Video-to-Audio Generation
arxiv.org·22h
👁️Perceptual Coding
An enough week
blog.mitrichev.ch·1d·
Discuss: blog.mitrichev.ch
📈Linear programming
Contrastive Weak-to-strong Generalization
arxiv.org·22h
⧗Information Bottleneck
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
huggingface.co·1d·
Discuss: Hacker News
📊Learned Metrics
YouTube gets ~5% CTR lift on Shorts by replacing embedding tables with Semantic IDs
shaped.ai·1d
📊Feed Optimization
LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation
arxiv.org·22h
🧠Learned Codecs
FramePack Studio
framepack.studio·16h·
Discuss: Hacker News
🎬WebCodecs
Revisiting Mixout: An Overlooked Path to Robust Finetuning
arxiv.org·1d
🧠Learned Codecs
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
arxiv.org·22h
🧠Neural Codecs
Can AI Co-Design Distributed Systems? Scaling from 1 GPU to 1k
harvard-edge.github.io·4h·
Discuss: Hacker News
🎯Performance Proofs
Beyond Grid-Locked Voxels: Neural Response Functions for Continuous Brain Encoding
arxiv.org·22h
🧠Neural Codecs
Channel Simulation and Distributed Compression with Ensemble Rejection Sampling
arxiv.org·2d
⧗Information Bottleneck
No Bullshit Guide to Statistics prerelease
minireference.com·8h·
Discuss: Hacker News
🧮Kolmogorov Bounds
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
arxiv.org·22h
🧠Learned Codecs