arXiv:2505.12576v2 Announce Type: replace-cross Abstract: A key factor in effective Self-Supervised learning (SSL) is preventing dimensional collapse, where higher-dimensional representation spaces ($R$) span a lower-dimensional subspace. Therefore, SSL optimization strategies involve guiding a model to produce $R$ with a higher…
arXiv:2501.17384v2 Announce Type: replace-cross Abstract: Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are increasingly prone to overfitting. For instance, a…
arXiv:2510.06527v1 Announce Type: new Abstract: We establish that randomly initialized neural networks, with large width and a natural choice of hyperparameters, have nearly independent outputs exactly when their activation function is nonlinear with zero mean under the Gaussian measure: $mathbb{E}_{z…
arXiv:2410.22371v3 Announce Type: replace Abstract: Stochastic differential equations are commonly used to describe the evolution of stochastic processes. The state uncertainty of such processes is best represented by the probability density function (PDF), whose evolution is governed by the Fokker-Planck…
arXiv:2510.06525v1 Announce Type: new Abstract: Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an attacker must first deanonymize the models behind displayed outputs — a threat…
arXiv:2208.08132v4 Announce Type: replace Abstract: Meta-learning is an effective method to handle imbalanced and noisy-label learning, but it depends on a validation set containing randomly selected, manually labelled and balanced distributed samples. The random selection and manual labelling and balancing…
arXiv:2510.06505v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection plays a crucial role in ensuring the robustness and reliability of machine learning systems deployed in real-world applications. Recent approaches have explored the use of unlabeled data, showing potential for enhancing OOD…
arXiv:2510.07193v1 Announce Type: cross Abstract: Quantum learning from remotely accessed quantum compute and data must address two key challenges: verifying the correctness of data and ensuring the privacy of the learner’s data-collection strategies and resulting conclusions. The covert (verifiable) learning…
arXiv:2510.06503v1 Announce Type: new Abstract: Accurate time-series predictions in machine learning are heavily influenced by the selection of appropriate input time length and sampling rate. This paper introduces ATLO-ML, an adaptive time-length optimization system that automatically determines the optimal input…
arXiv:2510.07117v1 Announce Type: cross Abstract: Physical vulnerability and mortality are often seen as obstacles to be avoided in the development of artificial agents, which struggle to adapt to open-ended environments and provide aligned care. Meanwhile, biological organisms survive, thrive, and…
