"A Day in the Life of Sandrone" Marionette Animated Short | Genshin Impact #GenshinImpact# #Sandrone# #サンドローネ# He said I was a friend. A family member. He was happy to have a companion. He wanted me to live according to my own will. Now, I finally understand what he meant.

Game world models tend to generate pixels directly, but pose and geometry drift the longer you roll them out. Marionette simply gives up the parts that must be exact — to a renderer. Title: Marionette: Predicting World States, Rendering Geometry, Painting Appearance URL: A world model that delegates geometry, occlusion, and motion to a deterministic renderer and lets the neural net paint only appearance. Three highlights. 🎮 Highlight 1: Predict an explicit 276-D world state Instead of pixels, it predicts a 3D state of joints, root trajectory, and rotations via two-stage autoregression. Control is just overwriting an action token (like a player's button press). Forcing a wrong action shifts the pose by ~31% — proof the control truly bites. 📐 Highlight 2: A zero-parameter deterministic renderer Six closed-form operations turn state into pose-control video, so world consistency, occlusion order, and metric scale hold by construction. Long-horizon failures are fixed by rules (e.g. a terrain collider) without retraining appearance — cutting penetration by 66%. 🎨 Highlight 3: Video diffusion for appearance only A Wan2.2-Fun-5B diffusion paints photorealistic RGB on top of exact geometry. Even via predicted state, FVD is 831 (799 from recorded state, 975 for pixel-autoregressive) — no detectable fidelity loss. Exactness to deterministic compute, appearance to the neural net — a clean division of labor. #WorldModels# #GameAI#

Candidate for reelection Rep. Mariannette Miller Meeks (R-IA) (@RepMMM) encourages Republicans to get out and vote and to "like what we do on social media, be a keyboard warrior."

⚓ 3,000+ students race for marine future The 15th National Marine Vehicle Design and Manufacturing Competition kicked off at Beijing Institute of Technology (Zhuhai) on August 8. 1,176 teams from 92 universities competed in underwater vehicles, smart control systems and marine equipment. The event also featured teacher innovation and youth competitions, aiming to nurture talent from classrooms to the deep blue sea. 🌊⚙️ 📍 Beijing Institute of Technology (Zhuhai), Zhuhai #MarineTech# #Zhuhai# #OceanInnovation# #Engineering# #STEM# #FutureTalent# #Guangdong# #Competition# #UnderwaterVehicles# #BlueEconomy# #SmartManufacturing#

🐟 "Gesheng No. 1": Offshore floating farm "Gesheng No. 1," a deep-sea aquaculture platform, was spotted off Xiaozhizhou Island, with the Hong Kong-Zhuhai-Macao Bridge visible in the distance. As part of Guangdong's push for smart ocean farming, this platform shows how technology is reimagining the way we grow our seafood. 🐟🌉 📍 Off Xiaozhizhou Island, Guishan Town, Zhuhai #DeepSeaFarming# #Aquaculture# #GeshengNo1# #Zhuhai# #OceanEconomy# #BlueFood# #SmartFarming# #Guangdong# #MarineTech# #Seafood# #Sustainability#