Lists (5)
Starred repositories
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A Modular Toolkit for Robot Kinematic Optimization
ACE-Step: A Step Towards Music Generation Foundation Model
Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe
Human in the loop Reinforcement Learning suite
This is a repo to track the latest autoregressive visual generation papers.
🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.
Ray tracing and hybrid rasterization of Gaussian particles
F Lite is a 10B parameter diffusion model created by Freepik and Fal, trained exclusively on copyright-safe and SFW content.
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
MineWorld: A Real-time interactive world model on Minecraft
An interactive HTML pretty-printer for machine learning research in IPython notebooks.
A JAX research toolkit for building, editing, and visualizing neural networks.
Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
small auto-grad engine inspired from Karpathy's micrograd and PyTorch
📰 Must-read papers and blogs on Speculative Decoding ⚡️
Implementation of Latent Diffusion Planning (Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn)
ML framework featuring compile time checks and accelerated by a JIT compiler.
Open source, AI-native testing framework for web apps
keithhans / Frida
Forked from cmubig/FridaA robot painter designed to support human artists. CoFRIDA, Best Paper on HRI, ICRA 2024. FRIDA, Finalist for Best Paper in Deployed Systems, ICRA 2023.
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
A robot painter designed to support human artists. CoFRIDA, Best Paper on HRI, ICRA 2024. FRIDA, Finalist for Best Paper in Deployed Systems, ICRA 2023.
[CVPR 2025 DDADS] MObI: Multimodal Object Inpainting Using Diffusion Models
3
Updated Apr 12, 2025
A lightweight recreation of OS1/Samantha from the movie Her, running locally in the browser
Training scripts for a Marigold inspired Transparency Segmentation model using Stable Diffusion 3.5 and the Trans10k Dataset.
A TTS model capable of generating ultra-realistic dialogue in one pass.
DiffuLab is designed to provide a simple and flexible way to train diffusion models while allowing full customization of its core components.
Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset