Skywork open-sources Matrix-Game 4.0: game engine rules meet streaming neural rendering
lmoroney · x · 2026-10-16
Skywork AI released Matrix-Game 4.0, the latest in its open-source series of interactive world models, built on a game-engine-plus-video-model split.
- An executable game engine handles gameplay, physics, and player input, while a causal, few-step video model streams detailed frames from the engine's clean low-poly RGB output — dubbed streaming neural rendering.
- The result is real-time playable worlds with long-horizon memory and long-sequence video generation.
- MIT-licensed, with models, game assets, code and quick start published; the repo has 2.5k stars, and news includes RTX 5090-optimized inference.
More from Infra
- Meta picks Apple's MLX as preferred local inference platform; Muse Spark Open runs on two M5 Ultra Mac Studios — awnihannun · 2026-10-16
- Hugging Face scales Indic pretraining with 2.8T tokens and an open data pipeline — Hugging Face Blog · 2026-10-16
- First AA-AgentPerf results: NVIDIA Vera Rubin NVL72 delivers up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- Vera Rubin NVL72 first benchmarks: up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16