Verified65% confidenceEventExact time
In 2022, Google DeepMind and École Polytechnique Fédérale de Lausanne (EPFL) published results in Nature, using a deep reinforcement learning system to directly control tokamak magnetic field coil currents to maintain complex plasma configurations.
3
Sources
65%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
量子计算+AI超算如何破解核聚变燃料困境
hackernewshackernews7/6/2026
Related Claims
UnverifiedDeepMind于2021年在Nature上发表研究，展示机器学习在纯数学中的应用69% similarUnverifiedTensorFlow and PyTorch are led by Google and Meta respectively and are the two mainstream frameworks for deep learning.69% similarUnverifiedDeepMind's approach trains a single neural network policy that directly maps plasma states to control commands for all magnetic field coils, enabling stable maintenance of plasma configurations previously difficult to achieve, such as negative triangularity cross-sections and snowflake divertors.67% similarUnverifiedGoogle DeepMind's Genie series, Meta's V-JEPA, and NVIDIA's Cosmos platform are all exploring technical approaches to embedding physical constraints into generative models.67% similarUnverified2023年Google DeepMind和ETH Zurich的研究团队发表论文证明，在包含数十亿token的训练集中，仅需注入数百个精心设计的样本即可在特定条件下改变模型输出66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/218009API
curl https://kongchang.com/api/v1/knowledge/claims/218009MCP
get_claim(id=218009)