Generate any location from the real world in Minecraft with a high level of detail.

11.210% - Decompilation of Minecraft: Legacy Console Edition

Neuron in silicon, a demonstration neuromorphic compute tile for spiking neural networks

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

🎧 Your Personal Streaming Service

Write like a high-level language, run like C.

Open-source, self-hosted note-taking tool built for quick capture. Markdown-native, lightweight, and fully yours.

Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for both generative and discriminative modeling.

A highly compressive and high-quality neural audio codec for speech models.

Source code for the EMNLP 2025 paper “DM-Codec: Distilling Multimodal Representations for Speech Tokenization”

Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models

Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.

s&box is a modern game engine, built on Valve's Source 2 and the latest .NET technology, it provides a modern intuitive editor for creating games

Project template for decomp-toolkit

A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

NanoGPT (124M) in 3 minutes

Nano vLLM

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Implementation of Hippoformer, Integrating Hippocampus-inspired Spatial Memory with Transformers

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

A character-level language diffusion model trained on Tiny Shakespeare

Code for the blog "Neural audio codecs: how to get audio into LLMs"

Official Repo For Pixel-LLM Codebase

[ICLR 2026] pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

LongCat Audio Tokenizer and Detokenizer