xuanhan863
Follow
Stars
Align Anything: Training All-modality Model with Feedback
[PyTorch] Minimal codebase for MusicGen models
Attempt to create an Open Source Privacy Focused Rewind.ai Alternative for data capture
Repo of paper "Free Process Rewards without Process Labels"
Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence
Rust multiprovider generative AI client (Ollama, OpenAi, Anthropic, Groq, Gemini, Cohere, ...)
Kura is a simple reproduction of the CLIO paper which uses language models to label user behaviour before clustering them based on embeddings recursively. This helps us understand user behaviour on…
Here we will keep track of the latest AI Game Development Tools, including LLM, Agent, Code, Writer, Image, Texture, Shader, 3D Model, Animation, Video, Audio, Music, Singing Voice and Analytics. 🔥
Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
Framework to reduce autotune overhead to zero for well known deployments.
VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE
Memory-optimized training scripts for video models based on Diffusers
a family of versatile and state-of-the-art video tokenizers.
FastVideo is a lightweight framework for accelerating large video diffusion models.
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusion
How to reduce complexity and move faster? Just Postgres for everything.
CPP Implementation of "LightGlue: Local Feature Matching at Light Speed"
The Easiest Rust Interface for Local LLMs and an Interface for Deterministic Signals from Probabilistic LLM Vibes
AnyModal is a Flexible Multimodal Language Model Framework for PyTorch
Abbey is a self-hosted configurable AI interface with workspaces, document chats, YouTube chats, and more. Find our hosted version at https://abbey.us.ai.