arXiv:2512.01556v1 Announce Type: cross Abstract: Large language models (LLMs) often generate unreliable answers, while heuristic uncertainty methods fail to fully distinguish correct from incorrect predictions, causing users to accept erroneous answers without statistical guarantees. We address this issue through the…
arXiv:2512.00251v1 Announce Type: new Abstract: The increasing complexity of IoT edge networks presents significant challenges for anomaly detection, particularly in identifying sophisticated Denial-of-Service (DoS) attacks and zero-day exploits under highly dynamic and imbalanced traffic conditions. This paper proposes SD-CGAN, a…
arXiv:2404.13182v3 Announce Type: replace Abstract: Neural processes (NPs) are probabilistic meta-learning models that map sets of observations to posterior predictive distributions, enabling inference at arbitrary domain points. Their capacity to handle variable-sized collections of unstructured observations, combined with simple maximum-likelihood…
arXiv:2512.00260v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) offer a promising alternative to Multi-Layer Perceptron (MLP) by placing learnable univariate functions on network edges, enhancing interpretability. However, standard KANs lack probabilistic outputs, limiting their utility in applications requiring uncertainty quantification.…
arXiv:2506.01374v3 Announce Type: replace Abstract: While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven substantial performance improvements, but…
arXiv:2512.00272v1 Announce Type: new Abstract: Approximate machine unlearning aims to efficiently remove the influence of specific data points from a trained model, offering a practical alternative to full retraining. However, it introduces privacy risks: an adversary with access to pre-…
arXiv:2509.22017v2 Announce Type: replace Abstract: Bipartite knowledge graphs in niche domains are typically data-poor and edge-sparse, which hinders link prediction. We introduce AEGIS (Authentic Edge Growth In Sparsity), an edge-only augmentation framework that resamples existing training edges -either uniformly simple…
arXiv:2512.00283v1 Announce Type: new Abstract: Foundation models have revolutionized various fields such as natural language processing (NLP) and computer vision (CV). While efforts have been made to transfer the success of the foundation models in general AI domains to biology,…
arXiv:2511.12240v2 Announce Type: replace Abstract: Modern deep learning systems are typically deployed as open-loop function approximators: they map inputs to outputs in a single pass, without regulating how much computation or explanatory effort is spent on a given case. In…
arXiv:2512.00289v1 Announce Type: new Abstract: We develop a data-driven framework for learning and correcting non-autonomous vehicle dynamics. Physics-based vehicle models are often simplified for tractability and therefore exhibit inherent model-form uncertainty, motivating the need for data-driven correction. Moreover, non-autonomous dynamics…
