Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

[ICLR 26] TempFlow-GRPO (Temporal Flow GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation.

JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

Single-stage End-to-End Training for Tokenization and Generation

[CVPR2026 Highlight] Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens https://arxiv.org/abs/2603.19232

[CVPR 2026 Highlight] Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Official code repository for "Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?"

Helios: Real Real-Time Long Video Generation Model

BitDance & UniWeTok: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model.

[ICLR 2025] Binary Spherical Quantization + [CVPR 2026] Leech Spherical Quantization

Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"

A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, a…

Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

[CVPR 2026 Highlight🔥] MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE

A unified inference and post-training framework for accelerated video generation.

Official repository for “PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss”

Minute-long video generation at 24FPS.

The offical code of Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

DiP: Taming Diffusion Models in Pixel Space

Visual Causal Flow

Moonshot's most powerful model

Code for the NIPS17 paper "Stabilizing Training of Generative Adversarial Networks through Regularization"

Advancing Open-source World Models

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders