Time series data plays a pivotal role in a wide variety of fields but faces challenges related to privacy concerns. Recently, synthesizing data via diffusion models is viewed as a promising solution. However, existing methods still struggle to capture long-range temporal dependencies and complex channel interrelations. In this research, we aim to utilize the sequence modeling capability of a State Space Model called Mamba to extend its applicability to time series data generation. We firstly analyze the core limitations in State Space Model, namely the lack of consideration for correlated temporal lag and channel permutation. Building upon the insight, we propose Lag Fusion Mamba and Permutation Scanning Mamba, which enhance the model's ability to discern significant patterns during the denoising process. Theoretical analysis reveals that both variants exhibit a unified matrix multiplication framework with the original Mamba, offering a deeper understanding of our method. Finally, we integrate two variants and introduce Diffusion Mamba for Time Series (DiM-TS), a high-quality time series generation model that better preserves the temporal periodicity and inter-channel correlations. Comprehensive experiments on public datasets demonstrate the superiority of DiM-TS in generating realistic time series while preserving diverse properties of data.

Next POI recommendation plays a crucial role in delivering personalized location-based services, but it faces significant challenges in capturing complex user behavior and adapting to dynamic interest distributions. Most methods often provide insufficient modeling of implicit features in user trajectories, such as directional transitions and latent edge relationships, which are essential for understanding user behavior. Moreover, existing diffusion models, constrained by Gaussian priors, struggle to handle the diverse and evolving nature of user preferences. The lack of a unified scheduling for noise and sampling also limits the flexibility of diffusion models. In this paper, we propose a Unified Bridge-based Diffusion model (UB-Diff) for the next POI recommendation. UB-Diff incorporates a direction-aware POI transition graph learning, which jointly captures spatio-temporal and directional features. To overcome the limitations of Gaussian priors, we introduce a bridge-based diffusion POI generative model. It can achieve distribution translation from the user's historical distribution to the target distribution by learning a bridge to associate user behavior with POI recommendation, adapting to dynamic user interests. In the end, we design a novel intermediate function to unify the diffusion process, enabling precise control over noise scheduling and modular optimization. Extensive experiments on five real-world datasets demonstrate the superiority of UB-Diff over advanced baseline methods. Our code is available athttps://github.com/JKZuo/UBDiff.

Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to learn spatial-temporal representations. However, it encounters three key challenges: 1) the difficulty in selecting reliable negative pairs due to the homogeneity of variables, hindering contrastive learning methods; 2) overlooking spatial correlations across variables over time; 3) limitations of efficiency and scalability in existing self-supervised learning methods. To tackle these, we propose a lightweight representation-learning model ST-ReP, integrating current value reconstruction and future value prediction into the pre-training framework for spatial-temporal forecasting. And we design a new spatial-temporal encoder to model fine-grained relationships. Moreover, multi-time scale analysis is incorporated into the self-supervised loss to enhance predictive capability. Experimental results across diverse domains demonstrate that the proposed model surpasses pre-training-based baselines, showcasing its ability to learn compact and semantically enriched representations while exhibiting superior scalability.

Due to the poor illumination and the difficulty in annotating, nighttime conditions pose a significant challenge for autonomous vehicle perception systems. Unsupervised domain adaptation (UDA) has been widely applied to semantic segmentation on such images to adapt models from normal conditions to target nighttime-condition domains. Self-training (ST) is a paradigm in UDA, where a momentum teacher is utilized for pseudo-label prediction, but a confirmation bias issue exists. Because the one-directional knowledge transfer from a single teacher is insufficient to adapt to a large domain shift. To mitigate this issue, we propose to alleviate domain gap by incrementally considering style influence and illumination change. Therefore, we introduce a one-stage Dual-Teacher Bi-directional Self-training (DTBS) framework for smooth knowledge transfer and feedback. Based on two teacher models, we present a novel pipeline to respectively decouple style and illumination shift. In addition, we propose a new Re-weight exponential moving average (EMA) to merge the knowledge of style and illumination factors, and provide feedback to the student model. In this way, our method can be embedded in other UDA methods to enhance their performance. For example, the Cityscapes to ACDC night task yielded 53.8 mIoU (%), which corresponds to an improvement of +5% over the previous state-of-the-art. The code is available at https://github.com/hf618/DTBS.