arXiv:2510.12950v1 Announce Type: new Abstract: Foundation models trained on large-scale de-identified electronic health records (EHRs) hold promise for clinical applications. However, their capacity to memorize patient information raises important privacy concerns. In this work, we introduce a suite of black-box…
arXiv:2510.12957v1 Announce Type: new Abstract: Standard benchmark datasets, such as MNIST, often fail to expose latent biases and multimodal feature complexities, limiting the trustworthiness of deep neural networks in high-stakes applications. We propose a novel multimodal Explainable AI (XAI) framework…
arXiv:2510.12939v1 Announce Type: new Abstract: Reinforcement learning (RL) policies deployed in real-world environments must remain reliable under adversarial perturbations. At the same time, modern deep RL agents are heavily over-parameterized, raising costs and fragility concerns. While pruning has been shown…
arXiv:2510.12934v1 Announce Type: new Abstract: Physical systems that naturally perform energy descent offer a direct route to accelerating machine learning. Oscillator Ising Machines (OIMs) exemplify this idea: their GHz-frequency dynamics mirror both the optimization of energy-based models (EBMs) and gradient…
arXiv:2510.12927v1 Announce Type: new Abstract: We introduce a novel framework for Federated Class Incremental Learning, called Federated Gaussian Task Embedding and Alignment (FedGTEA). FedGTEA is designed to capture task-specific knowledge and model uncertainty in a scalable and communication-efficient manner. At…
arXiv:2506.11283v2 Announce Type: replace-cross Abstract: Many imaging modalities involve reconstruction of unknown objects from collections of noisy projections related by random rotations. In one of these modalities, cryogenic electron microscopy (cryo-EM), the extremely low signal-to-noise ratio (SNR) makes integration of…
arXiv:2510.12975v1 Announce Type: new Abstract: The local intrinsic dimension (LID) of data is a fundamental quantity in signal processing and learning theory, but quantifying the LID of high-dimensional, complex data has been a historically challenging task. Recent works have discovered…
arXiv:2508.19831v2 Announce Type: replace-cross Abstract: Evaluating instruction-tuned Large Language Models (LLMs) in Hindi is challenging due to a lack of high-quality benchmarks, as direct translation of English datasets fails to capture crucial linguistic and cultural nuances. To address this, we…
arXiv:2510.12981v1 Announce Type: new Abstract: Current unlearning metrics for generative models evaluate success based on reference responses or classifier outputs rather than assessing the core objective: whether the unlearned model behaves indistinguishably from a model that never saw the unwanted…
arXiv:2510.13744v1 Announce Type: cross Abstract: Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive full credit, each step must be not only correct but also sufficiently…
