Contrastive learning methods for time series anomaly detection (TSAD) heavily depend on the quality of negative sample construction. However, existing strategies based on random perturbations or pseudo-anomaly injection often struggle to simultaneously preserve temporal semantic consistency and provide effective decision-boundary supervision. Most existing methods rely on prior anomaly injection, while overlooking the potential of generating hard negatives near the data manifold boundary directly from normal samples themselves. To address this issue, we propose a reconstruction-driven boundary negative generation framework that automatically constructs hard negatives through the reconstruction process of normal samples. Specifically, the method first employs a reconstruction network to capture normal temporal patterns, and then introduces a reinforcement learning strategy to adaptively adjust the optimization update magnitude according to the current reconstruction state. In this way, boundary-shifted samples close to the normal data manifold can be induced along the reconstruction trajectory and further used for subsequent contrastive representation learning. Unlike existing methods that depend on explicit anomaly injection, the proposed framework does not require predefined anomaly patterns, but instead mines more challenging boundary negatives from the model's own learning dynamics. Experimental results show that the proposed method effectively improves anomaly representation learning and achieves competitive detection performance on the current dataset.

Preferences serve as an alternative but recent work rarely considers preference learning given multiple tasks.

Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning.

However, zero-shot learning methods still require human instruction set to solve a new task.

Extending this approach to other transformer-based image encoders presents several challenges.

Figure A.1: Among all hyperparameter combinations considered in our grid search, a combination of ( We used a compute time of approximately 5600 CPU-hours of 2.90GHz Intel Xeon Gold In this section, we outline our anomaly detection experimental setting in more detail. Given a dataset (e.g., CIFAR-10) with In contrast to the "one-vs-rest" setting, in LOO we define one class of the In both "one-vs-rest" and LOO AD settings, we evaluate model representations in the following way: We show the pairs of items that change the most in distance in Table B.1. "stethoscope", which are semantically unrelated but perhaps have some slight visual similarity, tend We show the results in Fig. B.1. Table B.1: Distances between pairs of individual items from THINGS, ranked by the relative change in cosine The top items move much closer together under naive alignment, while the bottom ones move much farther apart. Figure B.1: How does the global structure of the representations change after alignment?