[NeurIPS 2025] Pixel-Perfect Depth

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Implementation of Danijar's latest iteration for his Dreamer line of work

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

LongLive: Real-time Interactive Long Video Generation

tiny vision language model

A minimal implementation of DeepMind's Genie world model

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

[SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes

🎁 A collection of utilities for LeRobot.

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

An open source collection of animated, interactive & fully customizable React components for building memorable websites.

React Flow | Svelte Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev) or Svelte (https://svelteflow.dev). Ready out-of-the-box and infinitely cust…

收集整理一些在Seedream 4.0 下生成的令人惊艳的图片和提示词

[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

A curated collection of fun and creative examples generated with Nano Banana🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development…

[NeurIPS 2025] Improving Video Generation with Human Feedback

[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

SpatialGen: Layout-guided 3D Indoor Scene Generation

An open-source AI agent that brings the power of Gemini directly into your terminal.

An image retrieval model for any localization task

Open-source platform to build and deploy AI agent workflows.