[ICCV 2025 Highlights] Large-scale photo-realistic virtual worlds for embodied AI

Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

Official Code for Stable Cascade

[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

An agentic skills framework & software development methodology that works.

"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

omo; the best agent harness - previously oh-my-opencode

Helios: Real Real-Time Long Video Generation Model

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, e…

An autonomous agent that conducts deep research on any data using any LLM providers

Advancing Open-source World Models

The official code of Yume

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

RealSee3D: A multi-view RGB-D dataset combining real-world captures and procedurally generated scenes, with extensible annotations for diverse 3D vision research.

A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…

A unified framework for 3D Occupancy Prediction

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving (ICLR 2026)

[ICCV 2025] Official PyTorch Implementation of "Learning Self-supervised Part-aware 3D Hybrid Representations of 2D Gaussians and Superquadrics"

[ICCV 2025] Official PyTorch Implementation of "Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction""

[IJCV 2025] Smaller But Better: Unifying Layout Generation with Smaller Large Language Models

[IEEE TPAMI 2025] Privacy-Preserving Biometric Verification With Handwritten Random Digit String

[arXiv 25] OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities

[ICLR 2026] LongLive: Real-time Interactive Long Video Generation

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

[ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"