Decart’s new world model can simulate hours of photorealistic driving
TechCrunch AI4 days agoNew ToolDecart is launching Oasis 3, a real-time world model designed to generate photorealistic driving environments for autonomous vehicle testing. The headline says it can simulate hours of driving, while also noting there are caveats. The model is now available through an API, giving developers a way to build applications or testing workflows on top of it.
Why Video Agent Models Are Next — Ethan He, xAI Grok Imagine
Latent Space13 days agoOpinionLatent Space interviews Ethan He, who led Grok Imagine at xAI, about building the product in three months. The episode contrasts video generation with world models and explores why video agent models may become an important next step. It also argues that Grok Imagine remains underrated, while the supplied description does not include architecture details or benchmark results.
ESMFold2: The Bitter Lesson Is Coming for Proteins★ 74
Latent Space18 days agoCommentaryLatent Space interviews Biohub’s Alex Rives about ESMFold2 and the broader ESM protein modeling stack. The discussion centers on datasets versus inductive bias, and whether protein biology is entering its own Bitter Lesson era. The key implication is that large-scale evolutionary sequence data and open models may become foundations for structure prediction, interaction modeling, and programmable biology.
Waypoint-1.5：讓家用 GPU 也能運行高保真度互動式虛擬世界★ 75
Hugging Face Blog66 days agoReleaseAs artificial intelligence advances toward Embodied AI and real-world physical interaction, high-fidelity 3D simulation environments have long been an…
Google DeepMind 推出 Project Genie 實驗原型：讓 AI Ultra 用戶創造並探索無限互動世界★ 82
Google DeepMind Blog136 days agoReleaseGoogle DeepMind has officially opened its highly anticipated experimental research prototype, "Project Genie," to Google AI Ultra subscribers in the United…
推出 Waypoint-1：來自 Overworld 的即時互動式影片擴散模型★ 75
Hugging Face Blog145 days agoReleaseOverworld has officially launched a new model called "Waypoint-1" on the Hugging Face platform. It is a world model focused on "Real-time Interactive Video…
NVIDIA 推出 Cosmos Reason 2：為具身智能與物理 AI 注入先進推理能力★ 85
Hugging Face Blog159 days agoReleaseNVIDIA and Hugging Face have jointly announced the launch of the new Cosmos Reason 2 model, marking a major breakthrough in the fields of Physical AI and…
Google DeepMind 發表 Genie 3：可即時互動的世界模型新前沿★ 82
Google DeepMind Blog233 days agoReleaseGoogle DeepMind has officially unveiled its latest generation world model — Genie 3 — demonstrating a major breakthrough in generative AI's ability to…
NVIDIA 於 GTC 2025 為實體 AI 開發者帶來重大發表：推出全新開源模型與資料集★ 85
Hugging Face Blog453 days agoReleaseAt NVIDIA GTC 2025, NVIDIA unveiled a remarkable set of new open-source models and datasets for the field of "Physical AI" — also known as embodied…