AI world model events
AI world model events across five evolution stages.
The AI world model events layer is easier to scan when every signal is tied to the same five practical stages: explore, create, control, simulate, and build.Source-backed rail
Every AI world model event keeps the date, stage, and source signal visible.
The list stays chronological for readers and crawlers, while the stage labels connect each update back to the evolution wheel above.Google expands Project Genie with Street View-grounded worlds
Google added Street View grounding to Project Genie and began rolling the experimental prototype out to eligible Google AI Ultra subscribers globally.
Google DeepMindOfficial product update
Runway turns GWM-1 into a real-time character product surface
Runway said its new Characters system is built on GWM-1 and made the real-time conversational video agent available through the Runway API plus web and mobile apps.
RunwayOfficial product update
Ant Lingguang brings a world-model experience to mobile
Ant's Lingguang App was reported to add an 'Experience World Model' feature backed by LingBot-World-Fast, turning one image into a short explorable 3D scene on mobile.
Ant Group / RobbyantReported product signal
Tencent open-sources HY-Embodied-0.5 and extends it with 0.5-X
Tencent open-sourced HY-Embodied-0.5 for real-world embodied agents and then released the HY-Embodied-0.5-X enhancement with inference and training code.
Tencent Robotics X / HY Vision TeamOfficial open-source release
Alibaba launches HappyOyster for real-time world creation
Alibaba introduced HappyOyster as an open-ended world model product for creating, exploring, and directing immersive environments in real time.
Alibaba Token HubOfficial product launch
Tencent Hunyuan opens HY-World 2.0 for persistent 3D worlds
Tencent Hunyuan expanded HY-World 2.0 beyond its April release by publishing HY-Pano 2.0 inference code and weights on May 11, then world-generation inference code plus WorldStereo 2.0 weights on May 18.
Tencent HunyuanOfficial repository update
Robbyant releases LingBot-Map for streaming 3D reconstruction
Robbyant followed the LingBot-Map release with public evaluation scripts for KITTI and Oxford Spires, strengthening the model's reproducibility story for streaming 3D reconstruction.
Ant Group / RobbyantOfficial repository update
NVIDIA previews Cosmos 3 as a unifying physical-AI world model
At GTC 2026, NVIDIA said Cosmos 3 would unify synthetic world generation, physical-AI reasoning, and action simulation, then kept widening the public Cosmos surface through an open data-factory blueprint and GitHub repos that were still active in late May.
NVIDIAOfficial platform update
Robbyant publishes LingBot-VA for robot-control world modeling
Robbyant released LingBot-VA as a causal video-action world model that predicts visual dynamics and robot actions together.
Ant Group / RobbyantOfficial open-source release
Robbyant releases LingBot-VLA for embodied-AI control
Robbyant released LingBot-VLA as a vision-language-action foundation model for generalist robot manipulation, with public code, paper, and model checkpoints.
Ant Group / RobbyantOfficial open-source release
World Labs announces the World API
World Labs moved its world model work toward a programmable developer surface with the World API.
World LabsOfficial platform announcement
Project Sid frames many-agent simulation as an AI civilization experiment
Project Sid gives the timeline a society-layer signal: agents specialize, coordinate, trade, and transmit behavior inside a persistent Minecraft-based world.
AlteraOfficial project repository
Runway introduces GWM-1
Runway framed GWM-1 as a general world model direction that reaches beyond video into worlds, avatars, and robotics.
RunwayOfficial research announcement
World Labs launches Marble
Marble gave the world model category a concrete product surface: generated 3D worlds that can be explored and edited.
World LabsOfficial product launch
Google DeepMind announces Genie 3
Genie 3 placed interactive, navigable world generation near the center of the world model conversation.
Google DeepMindOfficial research announcement
NVIDIA launches Cosmos
NVIDIA introduced Cosmos as a world foundation model platform for physical AI development.
NVIDIAOfficial platform launch
Oasis demonstrates a realtime playable AI world
Oasis demonstrated an action-conditioned Minecraft-like world that can be generated frame by frame while the player moves.
Decart AI + EtchedOfficial project page
Skybox AI keeps the entry point simple: type a place, open a world
Skybox AI gives the timeline an early consumer-facing spatial signal: a generated world can start as a 360-degree horizon, mood, and environment shell.
Blockade LabsOfficial product surface