Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.00861v1 Announce Type: new Abstract: Adversarial optimization under a shared $\ell_1$ budget requires deciding not only how much perturbati…
arXiv:2610.00858v1 Announce Type: new Abstract: Background and Objective: Clinicians expect recurrence risk to climb with cancer severity. In a UK mul…
arXiv:2610.00838v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step i…
arXiv:2610.00835v1 Announce Type: new Abstract: Text-to-music generation models are trained on massive music collections, creating a growing need for…
arXiv:2610.00831v1 Announce Type: new Abstract: A typed decision is a choice among a fixed set of options, returned as a probability rather than as te…
arXiv:2610.00820v1 Announce Type: new Abstract: General-purpose models can adapt to many tasks from context, while specialised models can execute indi…
arXiv:2610.00818v1 Announce Type: new Abstract: Ambulance ramping, the delay between hospital arrival and patient handover, is a critical operational…
arXiv:2610.00814v1 Announce Type: new Abstract: Synthetic data are increasingly used to scale LLM training, yet more synthetic data do not necessarily…
arXiv:2610.00778v1 Announce Type: new Abstract: In goal-conditioned reinforcement learning (GCRL), quasimetric learning models goal-reaching costs as…
arXiv:2610.00771v1 Announce Type: new Abstract: A central puzzle in transfer learning is why pre-training on one task can accelerate training or impro…
arXiv:2610.00767v1 Announce Type: new Abstract: Pre-training interventions are critical to alignment research, since beliefs formed during pre-trainin…
arXiv:2610.00758v1 Announce Type: new Abstract: By learning transferable rewards, inverse reinforcement learning (IRL) enables counterfactual evaluati…
arXiv:2610.00753v1 Announce Type: new Abstract: End-to-end backpropagation has been the dominant mode of training in deep learning, allowing for the c…
arXiv:2610.00751v1 Announce Type: new Abstract: Recent theoretical work identified fundamental properties of representation geometry that shape infere…
arXiv:2610.00730v1 Announce Type: new Abstract: Mixed-integer linear programs (MILP) model many real-world decision problems, motivating machine-learn…
arXiv:2610.00729v1 Announce Type: new Abstract: This paper explores a reward-based policy to achieve zero-shot transfer between source and target envi…
arXiv:2610.00728v1 Announce Type: new Abstract: Weather reanalysis products rely on computationally intensive numerical weather predictions followed b…
arXiv:2610.00722v1 Announce Type: new Abstract: World models enable agents to plan by predicting future states of the environment, but their predictio…
arXiv:2610.00713v1 Announce Type: new Abstract: When a graph neural network (GNN) explainer produces an unexpected attribution on a molecule, the attr…
arXiv:2610.00708v1 Announce Type: new Abstract: Data-driven Riemannian geometry provides nonlinear interpolation and geometric representations of high…