Stars
A tool for burning visible pictures on a compact disc surfase
Injectorpp is a powerful tool designed to facilitate the writing of unit tests without the need to introduce traits solely for testing purposes. It streamlines the testing process by providing a se…
A simple, decentralized mesh VPN with WireGuard support.
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
A Rust crate for cooking up terminal user interfaces (TUIs) 👨🍳🐀 https://ratatui.rs
A Python library for amortized Bayesian workflows using generative neural networks.
Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.
A new pure-Rust library for cross-platform low-level access to USB devices.
Krita is a free and open source cross-platform application that offers an end-to-end solution for creating digital art files from scratch built on the KDE and Qt frameworks.
2D vector & raster editor that melds traditional layers & tools with a modern node-based, non-destructive, procedural workflow.
Official repository for "AM-RADIO: Reduce All Domains Into One"
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
Train transformer language models with reinforcement learning.
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
verl: Volcano Engine Reinforcement Learning for LLMs
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
Minimal reproduction of DeepSeek R1-Zero
Powerful, mature open-source cross-platform game engine for Python and C++, developed by Disney and CMU
Janus-Series: Unified Multimodal Understanding and Generation Models
Official implementation of "VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment"