Realizing endogenous narrative evolution in LLM-based multi-agent systems is hindered by the inherent stochasticity of generative emergence.In particular, long-horizon simulations suffer from social memory stacking, where conflicting relational states accumulate without resolution, and narrative-spatial dissonance, where spatial logic detaches from the evolving plot.To bridge this gap, we propose EVOSPARK, a framework specifically designed to sustain logically coherent long-horizon narratives within endogenous interactive agent societies.To ensure consistency, the stratified narrative memory employs a role socio-evolutionary base as living cognition, dynamically metabolizing experiences to resolve historical conflicts.Complementarily, a Generative Mise-en-Scène mechanism enforces role-location-plot alignment, synchronizing character presence with the narrative flow.Underpinning these is the unified narrative operation engine, which integrates an Emergent Character Grounding Protocol to transform stochastic sparking into persistent characters.This engine establishes a substrate that expands a minimal premise into an open-ended, evolving story world.Experiments demonstrate that EVOSPARK significantly outperforms baselines across diverse paradigms, enabling the sustained generation of expressive and coherent narrative experiences.

Pruning is widely researched as one of the effective methods for model compression. However, existing pruning methods still have shortcomings in achieving high model compression rates and maintaining model performance. To this end, we propose a general method called Channel And Space Pruning (CSP) for compressing deep convolutional neural networks (DCNNs). The proposed CSP method comprises Coarse-grained pruning and Fine-grained pruning, which operate on the convolutional kernels from both channel and spatial dimensions to achieve model compression. The Coarse-grained pruning utilizes a Bottleneck-based maximum flow mechanism to ensure maximum flow of inputs and outputs in DCNNs, thereby maintaining model performance. Additionally, a Bottleneck-based dynamic updating mechanism is employed to evaluate the importance of convolutional kernels, allowing for the pruning of redundant kernels while maintaining model performance. The Fine-grained pruning further compresses the model based on Coarse-grained pruning. To ensure that the parameters of the convolutional kernels obtained through Coarse-grained pruning are not spatially redundant, Fine-grained pruning employs the Parameters-free spatial attention mechanism (PSAM) for spatial sparsification of the kernels. The proposed CSP method demonstrates promising results compared to state-of-the-art (SOTA) methods in classic DCNN models.

3D perception of objects is critical for many real-world applications, such as autonomous cars and robots. Among them, most state-of-the-art (SOTA) 3D perception systems are based on deep learning models. Recently, the research community found that 3D object classifiers on point cloud based on deep learning are easily fooled by adversarial point cloud craft by attackers. To overcome this, adversarial defenses are considered the most effective ways to improve the robustness of deep learning models, and most adversarial defenses on point cloud are focused on input transformation. However, all previous defense methods decrease the natural accuracy, and the nature of the point cloud classifiers itself has been overlooked. To this end, in this paper, we propose a novel adversarial defense for 3D point cloud classifiers that makes full use of the nature of the point cloud classifiers. Due to the disorder of point cloud, all point cloud classifiers have the property of permutation invariant to the input point cloud. Based on this nature, we design invariant transformations defense (IT-Defense). We show that, even after accounting for obfuscated gradients, our IT-Defense is a resilient defense against SOTA 3D attacks. Moreover, IT-Defense does not hurt clean accuracy compared to previous SOTA 3D defenses. Our code will be available at: https://github.com/cuge1995/IT-Defense.

Tail-sitter unmanned aerial vehicles (UAVs) have gained extensive popularity in recent years due to their inherent advantages of both fixed wing and rotary wing UAVs. However, these advantages are accompanied with control challenges because of two different flight regimes and drastically changing dynamics during transition flights. This paper focuses on the design of a unified controller free from cumbersome controller switchings and applicable in all attitude range for a tail-sitter with single thrust-vectored propeller. To achieve this, both thrust vectoring model and full-regime aerodynamics model are built first, after which a complete attitude dynamics model of the tail-sitter is established utilizing the quaternion attitude description to avoid the singularity problem. An adaptive controller is then derived based on a simplified model using the Lyapunov stability theory with unknown system parameters identified online by forgetting factor recursive least square (FF-RLS) method. Flight experiments are conducted to demonstrate the feasibility and effectiveness of the proposed control scheme.

This paper discusses the design and control methods of a thrust-vectored tailsitter that combines the advantages of both fixed wing and rotary wing systems. Separable takeoff bracket and controllable forward landing are implemented to reduce the flight weight and mitigate the effects of crosswinds. A six-degrees-of-freedom model especially for this tailsitter is then proposed to describe the dynamics of the whole system. Attitude representation based on horizontal /vertical Euler angles is presented to avoid the problem of singularity. Attitude and altitude controllers that switch between horizontal and vertical modes are used. In these controllers linear/constant acceleration approximation and filtered feed-forward acceleration algorithm are implemented. Effectiveness and reliability of the proposed control methods are demonstrated and evaluated by experimental results of the whole flight envelope.

This paper focuses on the design, modelling and hovering control of a tail-sitter with single thrust-vectored propeller which possesses the inherent advantages of both fixed wing and rotary wing unmanned aerial vehicles (UAVs). The developed tail-sitter requires only the same number of actuators as a normal fixed wing aircraft and achieves attitude control through deflections of the thrust-vectored propeller and ailerons. Thrust vectoring is realized by mounting a simple gimbal mechanism beneath the propeller motor. Both the thrust vector model and aerodynamics model are established, which leads to a complete nonlinear model of the tail-sitter in hovering state. Quaternion is applied for attitude description to avoid the singularity problem and improve computation efficiency. Through reasonable assumptions, a simplified model of the tail-sitter is obtained, based on which a backstepping controller is designed using the Lyapunov stability theory. Experimental results are presented to demonstrate the effectiveness of the proposed control scheme.