Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.01425v1 Announce Type: new Abstract: Train-validation separation is the evolving difference between performance on observed training exampl…
arXiv:2610.01399v1 Announce Type: new Abstract: Among on-policy deep reinforcement learning methods, Proximal Policy Optimization (PPO) has become the…
arXiv:2610.01395v1 Announce Type: new Abstract: Muon improves large-scale training by applying a spectral-norm steepest-descent update to matrix param…
arXiv:2610.01384v1 Announce Type: new Abstract: Reliable uncertainty quantification is essential for deploying deep learning models in high-stakes set…
arXiv:2610.01377v1 Announce Type: new Abstract: We study causal logistic bandits with counterfactual fairness constraints. The causal structure is giv…
arXiv:2610.01375v1 Announce Type: new Abstract: A user's movie, news, and dialogue histories differ in their native actions and outputs, yet each inte…
arXiv:2610.01373v1 Announce Type: new Abstract: World models allow agents to plan in latent space by choosing a sequence of actions that most reduces…
arXiv:2610.01369v1 Announce Type: new Abstract: Understanding a nonlinear dynamical system from time series requires not only reproducing its trajecto…
arXiv:2610.01356v1 Announce Type: new Abstract: Stable port-Hamiltonian neural networks certify asymptotic stability by construction. Yet, their Hamil…
arXiv:2610.01355v1 Announce Type: new Abstract: We introduce a new framework for one-step generative modelling on finite state spaces. To extend drift…
arXiv:2610.01343v1 Announce Type: new Abstract: We study the classical single-machine scheduling problem of minimizing the sum of completion times of…
arXiv:2610.01322v1 Announce Type: new Abstract: We introduce the Clifford Sheaf Neural Network (CSNN), an equivariant sheaf neural network for geometr…
arXiv:2610.01318v1 Announce Type: new Abstract: Model collapse arises when generative models are trained on synthetic data produced by earlier models.…
arXiv:2610.01317v1 Announce Type: new Abstract: Evaluating candidate architectures in neural architecture search (NAS) faces an inherent trade-off: on…
arXiv:2610.01315v1 Announce Type: new Abstract: Generative models have made rapid progress in ordered crystal structure prediction, yet many functiona…
arXiv:2610.01284v1 Announce Type: new Abstract: Model validation estimates the performance of a complete learning procedure on new data. However, an i…
arXiv:2610.01270v1 Announce Type: new Abstract: Personalization encoders compress evolving interaction histories into preference states used to rank i…
arXiv:2610.01269v1 Announce Type: new Abstract: Bayesian Optimisation (BO) is a powerful framework for the optimisation of expensive black-box functio…
arXiv:2610.01253v1 Announce Type: new Abstract: Quantum Reinforcement Learning (QRL) integrates reinforcement learning with parameterized quantum circ…
arXiv:2610.01238v1 Announce Type: new Abstract: Unified language models are increasingly expected to combine heterogeneous capabilities, such as mathe…