Game-native world model adds 108M-frame dataset and explicit state supervision

Scobleizer · x · 2026-07-24

Video world models generate pixels; games run on state. This post introduces a game-native world model centered on an explicit, evolving world state.

• WildWorld: a dataset of 108M+ frames with actions and explicit state ground truth.
• From Pixels to States: Rethinking Interactive World Models as Game Engines: the accompanying paper framing interactive world models as stateful game engines.
• The diagram emphasizes a loop of action → state → observation, aiming for real-time interactive generation with persistent state-observation consistency.

Original post →

More from Multimodal

• A creator built a 4-minute animated short with FLUX.1 Dev and LTX-Video 2.3 — developervkmp · 2026-07-24
• VCSD boosts Qwen3-VL on ViRL39K without external teachers or evidence — UMCP · 2026-07-24
• A new pixel-space benchmark says image generators can reason spatially, but text VLMs still lead — OmniAI-ZJU · 2026-07-24
• Higgsfield’s MCP turns Claude into a no-code video studio with one URL — socialwithaayan · 2026-07-24
• A Claude plus video-model workflow can now turn one sentence into a 10-minute documentary — PrajwalTomar_ · 2026-07-24
• New Midjourney style shared with exact prompt settings and example images — azed_ai · 2026-07-24

Multimodal channel →