Examples include early diagnosis of medical diseases [22], threat detection for cyber-attacks [3, 18, 36], or safety analysis for self-driving cars [38]. Manyreal-world anomalies can be detected intime series data.

Determinantal point processes (DPPs) are well-suited to recommender systems where the goal is to generate collections of diverse, high-quality items.

Subsequently, we select train-test splits from the same iteration steps. These settings are used throughout our study. For the few-shot experiments, the same pipeline parameters were utilized with changes noted in the respectivesection. However,thefactthatFIDscores are relatively close to another despite large semantic differences between datasets may indicate that FID based on our utilised FID estimator (Sec. Beyond these limits, generic representations learned byself-supervised learning may offerbetter zero-shot generalization,asalsodiscussedonSec.

This is the state-of-the-art graph contrastive learning based recommendation method, which proposes randomly node dropout, edge dropout, and random walk for augmentation onthebipartite graph.

Semantic IDs created using an auto-encoder (RQ-V AE [40, 21]) for retrieval models. We refer to V ector Quantization as the process of converting a high-dimensional vector into a low-dimensional tuple of codewords. We discuss this technique in more detail in Subsection 3.1. We use users' review history During training, we limit the number of items in a user's history to 20. The results for this dataset are reported in Table 7 as the row'P5'.

Organizations handling sensitive documents face a critical dilemma: adopt cloud-based AI systems that offer powerful question-answering capabilities but compromise data privacy, or maintain local processing that ensures security but delivers poor accuracy. We present a question-answering system that resolves this trade-off by combining semantic understanding with keyword precision, operating entirely on local infrastructure without internet access. Our approach demonstrates that organizations can achieve competitive accuracy on complex queries across legal, scientific, and conversational documents while keeping all data on their machines. By balancing two complementary retrieval strategies and using consumer-grade hardware acceleration, the system delivers reliable answers with minimal errors, letting banks, hospitals, and law firms adopt conversational document AI without transmitting proprietary information to external providers. This work establishes that privacy and performance need not be mutually exclusive in enterprise AI deployment.

Various neuroimaging studies suffer from small sample size problem which often limit their reliability. Meta-analysis addresses this challenge by aggregating findings from different studies to identify consistent patterns of brain activity. However, traditional approaches based on keyword retrieval or linear mappings often overlook the rich hierarchical structure in the brain. In this work, we propose a novel framework that leverages hyperbolic geometry to bridge the gap between neuroscience literature and brain activation maps. By embedding text from research articles and corresponding brain images into a shared hyperbolic space via the Lorentz model, our method captures both semantic similarity and hierarchical organization inherent in neuroimaging data. In the hyperbolic space, our method performs multi-level neuroimaging meta-analysis (MNM) by 1) aligning brain and text embeddings for semantic correspondence, 2) guiding hierarchy between text and brain activations, and 3) preserving the hierarchical relationships within brain activation patterns. Experimental results demonstrate that our model outperforms baselines, offering a robust and interpretable paradigm of multi-level neuroimaging meta-analysis via hyperbolic brain-text representation.