Exponential Error Bounds for Information Bottleneck Source Coding Problems
arxiv.orgยท15h
๐Ÿ“Compression Bounds
How JPEG Works: The Subtle Beauty and Art of Imperfection
techspot.comยท1d
๐Ÿ–ผ๏ธJPEG XL
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
huggingface.coยท1dยท
Discuss: Hacker News
๐Ÿ“ŠLearned Metrics
A small rant about compression
codecs.multimedia.cxยท2d
๐Ÿ“ฆDeflate
Explicit Lossless Vertex Expanders!
gilkalai.wordpress.comยท9h
๐Ÿ’ŽInformation Crystallography
In-Depth Analysis: "Attention Is All You Need"
dev.toยท3hยท
Discuss: DEV
๐Ÿง Intelligence Compression
Detecting and Mitigating Insertion Hallucination in Video-to-Audio Generation
arxiv.orgยท15h
๐Ÿ‘๏ธPerceptual Coding
An enough week
blog.mitrichev.chยท23hยท
๐Ÿ“ˆLinear programming
FramePack Studio
framepack.studioยท9hยท
Discuss: Hacker News
๐ŸŽฌWebCodecs
Contrastive Weak-to-strong Generalization
arxiv.orgยท15h
โง—Information Bottleneck
No Bullshit Guide to Statistics prerelease
minireference.comยท1h
๐ŸงฎKolmogorov Bounds
LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation
arxiv.orgยท15h
๐Ÿง Learned Codecs
Revisiting Mixout: An Overlooked Path to Robust Finetuning
arxiv.orgยท1d
๐Ÿง Learned Codecs
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
arxiv.orgยท15h
๐Ÿง Neural Codecs
Beyond Grid-Locked Voxels: Neural Response Functions for Continuous Brain Encoding
arxiv.orgยท15h
๐Ÿง Neural Codecs
Channel Simulation and Distributed Compression with Ensemble Rejection Sampling
arxiv.orgยท2d
โง—Information Bottleneck
Generative Art
4rknova.comยท1dยท
Discuss: Hacker News
๐Ÿ“Mathematical Art
NExF: Learning Neural Exposure Fields for View Synthesis
m-niemeyer.github.ioยท12hยท
Discuss: Hacker News
๐Ÿ“ŠLearned Metrics
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
arxiv.orgยท15h
๐Ÿง Learned Codecs
Optimal Stopping in Latent Diffusion Models
arxiv.orgยท15h
๐Ÿง Machine Learning