REFINE: Trajectory Representation Learning via Closed-Loop Transcription
针对轨迹表示学习中现有方法的局限性,提出REFINE框架,通过闭环转录精炼结合反馈控制理论,提升模型对局部和全局时空依赖性的捕捉能力。
针对轨迹表示学习中现有方法的局限性,提出REFINE框架,通过闭环转录精炼结合反馈控制理论,提升模型对局部和全局时空依赖性的捕捉能力。
Catastrophic forgetting severely hinders long-term adaptability in continual learning. This paper proposes the first Mamba-based, forgetfulness-free fine-tuning framework for class-incremental continual learning. Our method maps historical task features into a subspace and applies orthogonal parameter updates within its nullspace—thereby preserving output consistency of the State Space Model (SSM) core across tasks. We theoretically derive and enforce consistency constraints on four time-invariant SSM parameters, simplifying both the recurrent structure and discretization procedure. Crucially, this work introduces nullspace projection to the Mamba architecture for the first time, enabling efficient, replay-free, and regularization-free continual learning. Evaluated on four standard class-incremental benchmarks, our approach consistently outperforms state-of-the-art methods. The implementation is publicly available.
This work addresses beamforming design for joint target sensing and active physical-layer eavesdropping (JTSAPE) systems, where a shared waveform at the base station simultaneously enables radar-like target parameter estimation, conveys information to the legitimate receiver, and acts as artificial noise to jam the illegitimate receiver—thereby enhancing eavesdropping performance. We propose the first normalized weighted framework jointly optimizing sensing accuracy (by minimizing the Cramér–Rao bound) and eavesdropping efficacy (by maximizing the eavesdropping signal-to-interference-plus-noise ratio). To tackle the resulting non-convex optimization under strong eavesdropper channels, we develop a stepwise iterative algorithm based on sequential rank-one constraint relaxation (SROCR). Simulation results demonstrate that the proposed method significantly improves both SINR and estimation accuracy in multi-target and time-varying channel scenarios, yielding high-quality suboptimal beam covariance solutions with strong robustness and practical applicability.
本文提出了一种基于捏合天线的集成感知与通信架构,通过动态重构辐射点来应对动态用户和目标,实现灵活且低成本的解决方案。
针对多视图城市区域表示学习中因共享潜在因素导致的误导性关联问题,提出CURE框架,通过估计并减少共享潜成分的影响来增强预测稳定性。
本文提出了一种基于捏合天线的集成感知与通信架构,通过动态重构辐射点来应对动态用户和目标,实现灵活且低成本的解决方案。
针对多视图城市区域表示学习中因共享潜在因素导致的误导性关联问题,提出CURE框架,通过估计并减少共享潜成分的影响来增强预测稳定性。
PACE框架通过联合控制答案源和等待窗口填充,以最小化感知首次响应时间(PTFR),提高对话服务质量。
为解决现有方法在跨场景泛化能力上的局限,DGCPath通过结合生成模型和分布对比学习,利用扩散视图生成器、变分对比机制及生成交叉监督模块提升路径表示学习的鲁棒性和可迁移性。
Nearest-neighbor classification is widely used in machine learning, yet existing methods often suffer from low computational efficiency and limited robustness in noisy environments. To jointly address these challenges, this paper proposes an efficient and reliable weighted $K$-nearest neighbor classification framework based on quantum granular balls, termed QGB-W$k$NN. The proposed framework improves computational efficiency by integrating quantum-enhanced granular-ball representation with hierarchical nearest-neighbor search, while enhancing classification reliability through a purity-aware weighted decision mechanism. Specifically, quantum-kernel granular balls are constructed to reduce retrieval redundancy and strengthen nonlinear feature representation under limited quantum resources. A granular-ball purity-guided HNSW optimization strategy is developed to exploit structural reliability for hierarchical graph construction during neighbor retrieval, alleviating the local optimality issue caused by conventional random layering. Finally, a weighted voting mechanism jointly incorporating granular-ball similarity and purity is introduced to produce more reliable classification decisions in noisy environments. Extensive experiments on benchmark datasets demonstrate that QGB-W$k$NN achieves competitive classification accuracy while exhibiting favorable Pareto trade-offs between classification performance and computational cost. Moreover, the proposed framework consistently improves robustness under various noisy conditions, suggesting that reliability-aware quantum granular-ball learning provides a promising paradigm for efficient and robust nearest-neighbor classification.