While many animals exhibit impressive hopping capabilities, machines have struggled to match their performance. Current hopping robots face limitations in power density, energy efficiency, and control stability. Here, we present a parallel-elastic actuation mechanism with a reactive latch that optimizes energy transfer, enabling a legged robot to achieve hopping heights and continuity previously unattainable. This mechanism efficiently stores and releases energy, extending the actuation period over the aerial phase while minimizing stance time. Our robot achieves a maximum hopping height of 3.6 meters, surpassing both human and animal records while demonstrating sustained, high-frequency hopping cycles with minimal power requirement. By integrating inertia-based onboard sensorimotor autonomy, we demonstrate stable, controlled hopping in environments without external aid. These results represent a step toward bridging the performance gap between biological and robotic locomotion, with potential to influence the design of future legged systems.

The influence maximization (IM) problem identifies a set$S$of$k$seed nodes from a social network$G$to maximize the expected number of nodes activated through an information diffusion process initiated by$S$. With the broad adoption of IM in sensitive societal domains, including healthcare, education, and recruitment, fairness-aware IM (FIM), which not only maximizes the influence spread but also ensures its proportional distribution between different groups in the population of$G$, has attracted much attention recently. However, existing FIM methods only work under the non-adaptive setting, where all seed nodes must be selected before any influence result is observed. In this paper, we investigate the problem of fairness-aware adaptive IM (FAIM), where the$k$seed nodes are selected in$B=\lceil k / r\rceil$batches of equal size$r$, so that the choice of the$b$-th batch can be made after the influence results of the previous$b-1$batches of seeds have been observed for each$b \in[B]$. We propose FAIM-RL, a new reinforcement learning framework for FAIM. Specifically, by formulating FAIM as a Markov decision process (MDP), the FAIM-RL framework leverages graph neural networks (GNNs) for influence- and topology-based node representations and a deep Q-network (DQN) for expected return estimation, so as to select seed nodes that can strike a balance between maximizing influence spread and ensuring group fairness in each batch. Extensive experiments on four real-world and synthetic network datasets demonstrate that FAIM-RL achieves significantly better trade-offs between influence and fairness metrics than state-of-the-art IM methods. Our code and data are publicly available at https://github.com/fzzf09/FAIM-RL.

Fairness in information access on social networks has been actively investigated in recent years. Most existing studies on this topic focus on the problem of Fair Influence Maximization (FIM), which aims to select a set of seed nodes such that a propagation campaign initiated by them has fair influence spread across different groups. Although FIM approaches can guarantee fair access to specific information, they cannot resolve the inherent disparities in information access between different groups arising from graph structures. To address this issue, we study the problem of augmenting the graph structure via edge suggestion towards fairer information access at the group level. Specifically, we formulate a new optimization problem called Fair Information Access via Edge Suggestion (FIAES) that identifies a set of at most b non-existing edges to be added into the graph such that they not only maximally increase the total influence spread, but also ensure fairness in the sense that the influence spreads within different groups are proportional to their population sizes . Since FIAES is NP-hard and cannot be approximated within any constant factor, unless P = NP , we propose FIAES-RL, a reinforcement learning-based algorithm for edge selection that strikes a balance between influence and fairness objectives. Finally, with extensive experimentation on four synthetic and real-world networks, we demonstrate that FIAES-RL outperforms several state-of-the-art baseline methods for fairness-aware edge suggestion, reducing inequity in information access while significantly boosting information propagation.

Complex software systems often provide a large number of parameters so that users can configure them for their specific application scenarios. However, configuration tuning requires a deep understanding of the software system, far beyond the abilities of typical system users. To address this issue, many existing approaches focus on exploring and learning good performance estimation models. The accuracy of such models often suffers when the number of available samples is small, a thorny challenge under a given tuning-time constraint. By contrast, we hypothesize that good configurations often share certain hidden structures. Therefore, instead of trying to improve the performance estimation of a given configuration, we focus on capturing the hidden structures of good configurations and utilizing such learned structure to generate potentially better configurations. We propose ACTGAN to achieve this goal. We have implemented and evaluated ACTGAN using 17 workloads with eight different software systems. Experimental results show that ACTGAN outperforms default configurations by 76.22% on average, and six state-of-the-art configuration tuning algorithms by 6.58%-64.56%. Furthermore, the ACTGAN-generated configurations are often better than those used in training and show certain features consisting with domain knowledge, both of which supports our hypothesis.