This is your work, valued
IT programming graduate and researcher
LaserScanningMicroscope. An stm32-based LSM
TiTok-Video. 1D video tokenizer
docEval-tools. A reference-based metric for evaluating document-length translations
basic_autoencoder. Python
MOSS-Audio-Tokenizer. MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming and variable bitrates, delivering SOTA reconstruction and strong performance in generation and understanding—serving as a unified interface for next-generation native audio language models.
LeanVAE. [ICCV2025]LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
WF-VAE. [CVPR 2025🔥] Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
Cosmos-Tokenizer. A suite of image and video neural tokenizers
SEED-Voken. SEED-Voken: A Series of Powerful Visual Tokenizers
npq-vit. [ICLR 2025] Binary Spherical Quantization + [CVPR 2026] Leech Spherical Quantization
Turkberry. Yogurt & Donuts
