Stars
Official implementation of Log-linear Sparse Attention (LLSA).
A simple tool to generate voice datasets of characters from game BanG Dream Girls Band Party.
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.
[NeurIPS 2025 AI for Music Workshop] Vocal Reaction Model and Benchmark
A simple yet effective Audio-to-Midi Automatic Piano Transcription system
A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.
StreamDiffusion, Live Stream APP
An enhanced Wan2.2 Image-to-Video node specifically designed to fix the slow-motion issue in 4-step LoRAs (like lightx2v).
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech
Voiced/Unvoiced descrimination model from speech
Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think
"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai Tech Report Link: https://arxiv.org/abs/2512.10971
Open Source code for our paper, Steering Autoregressive Music Generation with Recursive Feature Machines (Zhao et al., 2025). aka MusicRFM
Trainging, inference, and testing of the SAC speech codec model.
A real-time face detection models built with YOLOv11n and fine-tuned on a custom Roboflow dataset.
Anime Face Detection using YOLOv8
Krea Realtime 14B. An open-source realtime AI video model.
explore AMT from the perspective of timbre
Implementation of "Hyperspherical Latents Improve Continuous-Token Autoregressive Generation"
Agentic IM Chatbot infrastructure that integrates lots of IM platforms, LLMs, plugins and AI features. ✨
Official Repo for Self-Forcing++ High Quality Long Video Generation