NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

KAE : KAN-based AutoEncoder (AE, VAE, VQ-VAE, RVQ, etc.)

Unofficial PyTorch implementation of Higgs Audio V2 Tokenizer with HuBERT semantic features. Complete training pipeline for semantic-acoustic audio tokenization with 960x downsampling and 8-layer RVQ.

On the Limits of Discrete Representations for Neural Control. A systematic empirical study of tokenization, quantization, and inductive bias in BCI (aka documented failures)

Vectorial language for digital consciousness - RVQ-based emotion encoding (DeepSeek R1 validated)

First-of-its-kind MIDI PCA RVQ VAE implementation and models

Residual vector quantization audio codec with a NumPy core: low-bitrate tokens for audio LMs, streaming encode/decode

NeuroRVQ biosignal tokenizer — pure Rust inference for EEG/ECG/EMG with Burn ML

Build pure-Rust NeuroRVQ inference to tokenize EEG, ECG, and EMG signals with Burn 0.20 and zero Python dependencies

Pytorch implementation of a Moshi-inspired audio LM based on multiple backbones, inlcuding Qwen and a transformer decoder.

AI-powered ultra-low bitrate audio codec CLI built on SNAC — Compress audio at 0.98-2.6 kbps with near-original quality (392:1 ratio vs WAV)

Vector-quantization compiler for LLM weights. Fits per-tensor RVQ codebooks, stores indices as bit-planes (~2 bits/weight), recovers quality with QAT, and exports to GGUF or vLLM.

APU-Codec: Neural audio codec from source, optimized for AMD APU tri-processor inference (NPU encoder, GPU decoder)