Starred repositories
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
A unified and fully open-source framework for instruction-guided and reference-guided video editing using natural language.
EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
[CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation.
Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence
[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
LLaVA-VLA: A Simple Yet Powerful Vision-Language-Action Model [ICRA 2026]
[ICCV 2025] Balanced Image Stylization with Style Matching Score
PyTorch code and models for VJEPA2 self-supervised learning from video.
[ICCVW 2025] This repository includes latest papers, projects and datasets on GenAI for Cel-Animation. Accepted by ICCV 2025 AISTORY Workshop.
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"
Enable AI to control your PC. This repo includes the WorldGUI Benchmark and GUI-Thinker Agent Framework.
Wan: Open and Advanced Large-Scale Video Generative Models
[ICML 2026]A Large-scale Dataset for training and evaluating model's ability on Dense Text Image Generation
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
FQGAN: Factorized Visual Tokenization and Generation
[IJCV 2025] Paragraph-to-Image Generation with Information-Enriched Diffusion Model