arXiv:2509.25278v1 Announce Type: cross Abstract: From clinical healthcare to daily living, continuous sensor monitoring across multiple modalities has shown great promise for real-world intelligent decision-making but also faces various challenges. In this work, we introduce MAESTRO, a novel framework that…
arXiv:2509.26322v1 Announce Type: cross Abstract: Counterfactual Explanations (CFEs) interpret machine learning models by identifying the smallest change to input features needed to change the model’s prediction to a desired output. For classification tasks, CFEs determine how close a given sample…
arXiv:2509.25351v1 Announce Type: cross Abstract: We examine gradient descent in matrix factorization and show that under large step sizes the parameter space develops a fractal structure. We derive the exact critical step size for convergence in scalar-vector factorization and show…
arXiv:2509.26507v1 Announce Type: cross Abstract: The relationship between computing systems and the brain has served as motivation for pioneering theoreticians since John von Neumann and Alan Turing. Uniform, scale-free biological networks, such as the brain, have powerful properties, including generalizing…
arXiv:2509.25482v1 Announce Type: cross Abstract: We present the design of an autoregressive active inference agent in the form of message passing on a factor graph. Expected free energy is derived and distributed across a planning graph. The proposed agent is…
arXiv:2409.17643v2 Announce Type: replace Abstract: There is a well known intrinsic trade-off between the fairness of a representation and the performance of classifiers derived from the representation. Due to the complexity of optimisation algorithms in most modern representation learning approaches,…
arXiv:2509.25519v1 Announce Type: cross Abstract: Flow models parameterized as time-dependent velocity fields can generate data from noise by integrating an ODE. These models are often trained using flow matching, i.e. by sampling random pairs of noise and target points $(mathbf{x}_0,mathbf{x}_1)$…
arXiv:2503.05321v2 Announce Type: replace Abstract: Riemannian metric learning is an emerging field in machine learning, unlocking new ways to encode complex data structures beyond traditional distance metric learning. While classical approaches rely on global distances in Euclidean space, they often…
arXiv:2509.25535v1 Announce Type: cross Abstract: In language tasks that require extensive human–model interaction, deploying a single “best” model for every query can be expensive. To reduce inference cost while preserving the quality of the responses, a large language model (LLM)…
arXiv:2505.01639v2 Announce Type: replace Abstract: L’evy processes are widely used in financial modeling due to their ability to capture discontinuities and heavy tails, which are common in high-frequency asset return data. However, parameter estimation remains a challenge when associated likelihoods…
