Highlights
- Pro
Stars
Build resilient language agents as graphs.
Mobile-Agent: The Powerful Mobile Device Operation Assistant Family
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A practical, first-principles handbook insp…
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
Open-source implementation of AlphaEvolve
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
PyTorchGeoNodes is a PyTorch module for differentiable shape programs / procedural models in forms of graphs. It can automatically translate Blender geometry node models into PyTorch code. Original…
[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner
[CVPR 2025] Official repository for "Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders"
SpatialLM: Training Large Language Models for Structured Indoor Modeling
Embedded graphics library to create beautiful UIs for any MCU, MPU and display type.
ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
李鲁鲁老师对 吴恩达《ChatGPT Prompt Engineering for Developers》课程中文版的实践
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
A sheet shows the evolution of Apple frameworks - Metal, ARKit, and RealityKit.
[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
An EWA surface splatter in WebGL
NVIDIA DLSS is a new and improved deep learning neural network that boosts frame rates and generates beautiful, sharp images for your games
A generative world for general-purpose robotics & embodied AI learning.
[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.