Leo
PulseAugur coverage of Leo — every cluster mentioning Leo across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
独立开发者为塔防游戏投入人力
独立游戏开发者、来自 6side Studio 的 Leo 讨论了他们即将推出的塔防游戏 Dawn of Defense。开发者强调，他们最新一期节目的创作过程投入了大量人力和时间，并明确表示其制作过程中未使用任何 AI。这种方法突显了对传统开发方法的承诺。
-
2026年5月将出现罕见的蓝月亮
2026年5月31日，夜空中将出现罕见的“蓝月亮”，这是同一个日历月内的第二个满月。这一天象事件虽然不会改变月亮的颜色，但因其罕见性而备受关注。此外，金星和木星在傍晚的天空中越来越近，将于6月9日达到近距离的合相。
-
LLMSpace framework models carbon footprint of LLMs on LEO satellites
Researchers have developed LLMSpace, a novel framework designed to model the carbon footprint associated with large language model inference on low Earth orbit (LEO) satellites. This framework accounts for both operatio…
-
Constraint-Aware Execution system plans hybrid space-ground compute workloads
Researchers have developed Constraint-Aware Execution (CAE), a planning system designed to optimize compute workloads for satellites. CAE addresses the challenge of limited downlink capacity by intelligently deciding wh…
-
Dueling DDQN optimizes LEO satellite network handovers, boosting throughput by 10.3%
Researchers have developed a new adaptive multi-objective handover framework for LEO satellite networks utilizing a dueling double deep Q-network (DDQN). This framework is designed to dynamically balance throughput, blo…
-
AI路由框架提升LEO卫星网络性能与效率
研究人员开发了一种新颖的、基于时空学习的分布式路由框架，专为动态低地球轨道（LEO）卫星网络设计。该框架将图注意力网络（GAT）和长短期记忆（LSTM）集成在深度Q网络（DQN）架构中，能够基于局部观测做出自适应路由决策。该系统被构建为一个部分可观察马尔可夫决策过程（POMDP），以处理动态网络条件和流量变化。仿真结果表明，与现有方法相比，吞吐量、丢包率、队列长度和端到端延迟均有显著改善，队列长度减少高达23.26%。此外，该方法还因…
-
Graph learning approach enhances SDN scalability for LEO mega-constellations
Researchers have developed a new software-defined networking (SDN) framework to manage the immense scale of Low Earth Orbit (LEO) satellite mega-constellations. This approach utilizes graph neural networks (GNNs) to mod…