Neural Compression, Machine Learning, Rate-Distortion, Entropy Models
Optimizing training a GPT style Tokenizer with C++
justinhj.github.io·2d
(1) Fitting hierarchical models in genetics, (2) A Stan model that runs faster with 400,000 latent parameters, (3) Super-scalable penalized maximum likelihood i...
statmodeling.stat.columbia.edu·9h
Morph: ChirpTransformer-based Encoder-decoder Co-design for Reliable LoRa Communication
arxiv.org·21h
Loading...Loading more...