Spiking Neural Networks (SNNs), due to their unique spike-based inference mechanism, offer low power consumption and biological plausibility. As a fundamental technology for various real-world applications, 3D point cloud analysis faces significant challenges related to high computational overhead and energy-intensive. In fact, each point can be viewed as a specialized spike data containing positional information in 3D space. Therefore, utilizing the spiking features of SNNs to represent point clouds holds significant potential. However, this exploration faces two main challenges: SNN-compatible architecture design and spike-based 3D spatial modeling. In this work, we introduce the SpikingPoint, a pure Spiking Multi-layer Perceptron (MLP) Architecture that leverages the low power consumption of SNNs and the computational efficiency of linear layers. Furthermore, we propose the spiking 3D Position Embedding (SPE) that effectively models the 3D spatial feature into spike-form features. SpikingPoint achieves competitive performance with a small number of parameters while reducing energy consumption. For example, when achieving similar accuracy, the theoretical energy consumption of our method is reduced by 97.1% compared to the mainstream ANN-based KPConv. With fewer parameters, SpikingPoint surpasses the state-of-the-art SNN-based P2SResLNet on ModelNet40 by 1.42% in accuracy.

Trust has been thoroughly investigated in human-human collaboration. As large language models advance, human-Al collaboration is becoming the future trend. Generative Al can act as a collaborator. However, limited research dedicated to exploring trust in human-Al collaboration. The degree of trust is intricately connected to both the user's reliance on the system and the system's perceived usefulness. Based on a human- Al collaborative writing dataset, this work employed cluster analysis to explore collaborative patterns in the process of human-Al collaboration. The results show that trust is dynamic, two-sided, and vague element. Meanwhile, based on the changes in trust, human-Al collaboration can be categorized into three types: increasing, curvilinear, and decreasing.

Spiking Neural Networks (SNNs) provide a sparse spike-driven mechanism which is believed to be critical for energy-efficient deep learning. Mixture-of-Experts (MoE), on the other side, aligns with the brain mechanism of distributed and sparse processing, resulting in an efficient way of enhancing model capacity and conditional computation. In this work, we consider how to incorporate SNNs’ spike-driven and MoE’s conditional computation into a unified framework. However, MoE uses softmax to get the dense conditional weights for each expert and TopK to hard-sparsify the network, which does not fit the properties of SNNs. To address this issue, we reformulate MoE in SNNs and introduce the Spiking Experts Mixture Mechanism (SEMM) from the perspective of sparse spiking activation. Both the experts and the router output spiking sequences, and their element-wise operation makes SEMM computation spike-driven and dynamic sparse-conditional. By developing SEMM into Spiking Transformer, the Experts Mixture Spiking Attention (EMSA) and the Experts Mixture Spiking Perceptron (EMSP) are proposed, which performs routing allocation for head-wise and channel-wise spiking experts, respectively. Experiments show that SEMM realizes sparse conditional computation and obtains a stable improvement on neuromorphic and static datasets with approximate computational overhead based on the Spiking Transformer baselines.