Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,712 papers.
9 Oct 2026
On-policy self-distillation promises to replace the sparse outcome signal of verifiable-reward RL with dense token-level credit: a teacher conditioned on the reference solution scores the student's own rollout, and the resulting distributional shift is distilled back into the…
9 Oct 2026
Nonlinear model predictive control (NMPC) can be applied to large nonlinear systems with complex objectives while enforcing constraints, but the cost of solving the underlying optimization problems limits real-time application for systems with fast dynamics or many states.
9 Oct 2026
Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection because they are more likely to yield informative group-relative learning signals, and prioritizing them can improve training…
9 Oct 2026
Generative modelling involves two complementary tasks: learning a probabilistic approximation of an unknown data distribution from observations, and designing a tractable mechanism for sampling from this approximation.
8 Oct 2026
Acquiring realistic microstructure data through Electron Backscatter Diffraction (EBSD) is costly and time consuming, often relying on specialised equipment. As microstructures strongly influence material properties, generating realistic samples is essential for modelling the…
8 Oct 2026
Reliable predictive uncertainty in Laplace approximations depends critically on the prior precision, yet selecting it requires a posterior sweep that is prohibitively expensive for neural networks with billions of parameters.
8 Oct 2026
We describe a 4-tensor attention model that predicts the next semantic state of a scene, for video generation and robot planning. A window of states has positions (x, t) and two fibers, a semantic fiber and a temporal-context fiber, and one softmax normalizes attention jointly…
8 Oct 2026
Puzzles are widely used to evaluate the reasoning capabilities of artificial intelligence (AI) systems for sequential decision making, yet approaches originating from different paradigms are rarely compared under unified conditions.
8 Oct 2026
General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has proven to be a useful tool for this goal, current RL pipelines depend on engineering-heavy, per-task structural priors…
8 Oct 2026
Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and benchmark score. We compare them as maps. A pretrained checkpoint is a base point in weight space, and a weight-space method is a smooth map from a small parameter space that starts…
8 Oct 2026
Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) agents offer a new way to approach BBO by combining task semantics, computation, optimization tools, and…
8 Oct 2026
Large language models are stochastic by nature. Repeated executions under the same experimental conditions may produce different responses. We propose a framework that can be applied across the model lifecycle, from task design to residual behavior and continuous monitoring.
8 Oct 2026
The kernel bandit problem consists of sequentially optimizing an unknown function with noisy feedback, where the function has bounded norm in a given Reproducing Kernel Hilbert Space (RKHS).
8 Oct 2026
Off-policy actor--critic methods control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere, regardless of how the critics disagree.
8 Oct 2026
Skillful prediction of biomass-burning activity several days in advance is important for air-quality forecasting and aerosol prediction. Two operational constraints motivate this work.
8 Oct 2026
Human Activity Recognition (HAR) using wearable or smartphone inertial sensors is commonly evaluated with both classical machine learning and deep learning methods. However, reported performance can be strongly affected by sensor modality, dataset characteristics, and…
8 Oct 2026
Ion correlations set the structure of polymer electrolytes and depend on the host permittivity, which is low and varies between polymers. A functional that carries these correlations from molecular simulations to larger inhomogeneous systems must transfer across domain sizes,…
8 Oct 2026
Automated methods have been proposed to overcome the limitations of human verbal deception detection, but evidence remains fragmented across disciplines. We systematically reviewed 25 years of research (289 reports, 6,136 classification models) and meta-analyzed 3,653 models…
8 Oct 2026
High-dimensional sparse recipe formulation in process industries involves nonlinear association of various covariates, bounded by sparsity constraints and multi-criteria tolerances.
8 Oct 2026
Learning and problem solving depend critically on the structure of internal representations. While many modern data-driven artificial systems achieve strong predictive performance, their learned representations often lack explicit structure for expressing abstraction,…
8 Oct 2026
Reinforcement learning in safety-critical domains requires maximizing task performance while strictly adhering to safety constraints. Existing safe reinforcement learning paradigms typically force a trade-off: they either require a priori knowledge to provide strict safety…
7 Oct 2026
Despite its widespread use, Proximal Policy Optimization with clipping (PPO-Clip) remains difficult to tune, and the interactions among critic learning, clipping, and rollout reuse remain incompletely understood.
7 Oct 2026
There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial results at least twice in a single financial year. UK annual reports are very lengthy documents with around 80 pages on average.
7 Oct 2026
Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using often-inaccessible original data. In this data-free regime, we analyze where forgetting occurs and why.