AI tools for World

DreamX-World is a general-purpose world model for creating high-fidelity interactive environments that can be explored, controlled, and transformed through actions and event pro

MolmoAct 2 is an open robotics foundation model from Ai2 designed to help robots perform real-world manipulation tasks with stronger perception and action reasoning. It focuses

LabOS is an AI-XR co-scientist platform for modern laboratories that connects agentic reasoning with real-world experiment execution. It is designed to help scientists move from

PhysForge is a framework for generating physics-grounded 3D assets for interactive virtual worlds and embodied AI environments. It addresses a limitation of many 3D generation s

Map2World is a segment-map conditioned text-to-3D world generation framework for creating explorable 3D environments from user-defined top-view layouts. It addresses limitations

SANA-WM is NVIDIA's efficient minute-scale world model for generating controllable 720p video from an initial image and a camera trajectory. It is designed to make long-horizon

Relit-LiVE is a video relighting framework that generates physically consistent and temporally stable relit videos. It is designed for changing illumination in real footage whil

Inspatio World is a real-time interactive 4D world model that turns a reference video into a dynamic explorable environment. It is designed for users who want to move beyond pas

HY World 2.0 is Tencent Hunyuan's open-source multimodal world model for reconstructing, generating, and simulating 3D worlds. It is designed as a broad world-modeling framework

Lyra 2 is an NVIDIA research system for explorable generative 3D worlds. It is designed to create camera-controlled walkthrough videos and lift them into 3D through feed-forward

OpenGame is an open-source agentic coding framework built to turn natural-language game ideas into playable web games. It is designed for the hard part of game creation: coordin

Talkie is a 13B vintage language model trained only on text from before 1931. It is designed to simulate interaction with a language model that has no direct knowledge of the mo

Multiworld is a scalable multi-agent, multi-view video world model designed to simulate environments where several agents act at the same time and must remain consistent across

Hybrid Memory is a research system for improving memory in dynamic video world models. It is designed to help generated worlds remember both stable scene information and changin

WildDet3D is a geometry-aware architecture for promptable 3D detection in the wild. It supports open-vocabulary monocular 3D object detection using text, point, and box prompts,

EditCrafter is a tuning-free high-resolution image editing method that uses pretrained text-to-image diffusion models. It is designed to edit images at resolutions far beyond th

Alaya Renderer is a generative world renderer that provides a scaling recipe for video generative rendering. It is designed around large-scale G-buffer data from AAA games, inve

DeepSeek V4 is an open-source large language model release from DeepSeek focused on cost-effective long-context reasoning, coding, and agentic capability. The preview includes D

Vista4D is a video reshooting framework that uses 4D point clouds to synthesize dynamic scenes from new camera trajectories and viewpoints. It is designed for cases where a sour

MMPhysVideo is a research system focused on multimodal physical reasoning for video. It is designed for tasks where video models must understand not only appearance and motion,