Lists (2)
Stars
[ICCV 2025] MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms
Text-driven human motion generation surveys, datasets and models.
Source code for CVPR 2025 paper: Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks
MIDI-LLM Official Transformers implementation (NeurIPS AI4Music '25)
Repository for MIDI-GPT, a controllable multi-track music machine.
Refactored / updated version of `stable-audio-tools` which is an open-source code for audio/music generative models originally by Stability AI.
Official repo of "Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs"
A curated list of research papers, resources, and advancements on Diffusion Cache and related efficient diffusion model acceleration techniques.
This repository collects papers on Human-Interaction-Motion-Generation applications. We will update new papers irregularly.
PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models
HumanML3D: A large and diverse 3d human motion-language dataset.
Generative models for conditional audio generation
An aggregation of human motion understanding research.
SHSans-derived CJK font family with a more concise & modern look. 未来荧黑·未來熒黑·ヒカリ角ゴ：基于思源黑体改造，拥有粗度和宽度系列，更加简明现代的超大字体家族。
AHN: Artificial Hippocampus Networks for Efficient Long-Context Modeling
Moe counter badge with multiple themes! - 多种风格可选的萌萌计数器
[ICLR 2026] Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache
The official implementation of our paper "Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning".
" Music Style Transfer with Time-Varying Inversion of Diffusion Models"
A paper list of spiking neural networks, including papers, codes, and related websites. 本仓库收集脉冲神经网络相关的顶会顶刊以及CNS论文和代码，正在持续更新中。
已实现蔚蓝档案自动战斗, 受blue_archive_auto_script启发制作的C++脚本框架
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation