Tag
A new paper introduces LPDS, a generative inverse modeling framework that maps desired fusion outcomes and target configurations to optimized laser pulse shapes for inertial confinement fusion, using multi-objective physics-constrained training and control mechanisms like constraint-conditioning and inpainting.
本文提出一个物理接地的多模态智能体框架，用于磁约束聚变装置中性束注入离子源的非平稳自适应调控，在EXL-50U平台455次放电的时序回放中验证了符号化物理量优于波形图像，并在监督运行下实现86.80%的束提取率。
Scientists overturned a 59-year-old belief about magnetic confinement fields in fusion reactors, and Google handed the breakthrough to Gemini agents, which discovered new solutions beyond the original researchers' findings — yielding two new approaches to plasma confinement.
A U.S. lawmaker asserts that commercialization of fusion energy, made feasible by AI plasma modeling, will transform society, and introduces a bipartisan bill to allocate $10 billion for its development.
Princeton and PPPL researchers successfully tested the PACMAN AI framework, which controls fusion plasma in real time with decisions made in 20 milliseconds and predicts instabilities.
Japan's government program is funding Helical Fusion with $400 million to advance stellarator-based fusion power towards demonstration in the 2030s, focusing on continuous operation and practical engineering milestones.
A podcast discussion covers AI applications in physical simulation, including scaling to trillion-parameter models, high-resolution weather forecasting, and plasma behavior prediction in fusion energy.
Inertia Enterprises has accelerated the production of fusion fuel pellets from days to minutes, a critical step towards commercializing fusion power plants.
The article explains the z-pinch technique for fusion, where a massive current through plasma creates a magnetic field that compresses it, as employed in magnetic plasma compression research at MIT.
Commonwealth Fusion Systems has published five peer-reviewed papers detailing the physics basis for its ARC fusion power plant, which is expected to produce 400 MW of electricity. The company's approach uses high-temperature superconductors to build a smaller, faster reactor.
An interactive web-based simulator lets users tweak parameters of a fusion power plant and instantly see resulting Q, efficiencies, and power flows.
DeepMind announces a research partnership with Commonwealth Fusion Systems to advance fusion energy using AI, leveraging deep reinforcement learning and the TORAX plasma simulator to optimize the SPARC tokamak's performance and accelerate the path to net fusion energy.