Lists (15)
Stars
Open data and scalable training for long-horizon video world models.
An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.
MAGI-2-preview: Scaling Video Generation Models Efficiently
[Official Repo] JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
a real-time digital-human model for long-form audio-video generation
Full-stack open-source interactive long-horizon world model.
Official implementation paper OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields
Infinite Worlds with Versatile Interactions
A beautiful, private, local-first personal finance tracker. Investments, net worth, spending, and simulations.
Multimodal RL training framework for diffusion & omni models
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
show latest commit message analyse reort for some popular repos
End-to-end realtime stack for connecting humans and AI
A framework for building realtime voice AI agents 🤖🎙️📹
A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation.
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
DreamX-World: A General-Purpose Interactive World Model
Infinite Interactive World Rollout on a Single Desktop GPU
Jiucaihua is a personal investment management Android app that helps users track stock and fund holdings, portfolio performance, and real-time market quotes.
Rust runtime for mobile and edge AI agents with remote tool execution over WebSocket.
open source style transfer model on par with nano banana pro, supporting Qwen-Image-Edit 2509, 2511, SenseNovaU1
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2