February 2026

We study gap-dependent performance guarantees for nearly minimax-optimal algorithms in reinforcement learning with linear function approximation. While prior works have established gap-dependent regret bounds in this setting, existing analyses do not apply to algorithms that achieve the nearly minimax-optimal worst-case regret bound $tilde{O}(dsqrt{H^3K})$, where $d$ is the feature dimension, $H$ is the horizon length, and $K$ is the number of episodes. We bridge this gap by providing the first gap-dependent regret bound for the nearly minimax-optimal algorithm LSVI-UCB++ […]

Ver mais

Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research explores a reverse curriculum generation approach that recursively decomposes complex datasets into simpler, more learnable components. We propose a teacher-student framework where the teacher is equipped with the ability to reason step-by-step, which is used to recursively generate easier versions of examples, enabling the student model to progressively master difficult […]

Ver mais

London, UK – As crypto-related fraud continues to evolve at speed across jurisdictions, C5 Group will convene leading legal practitioners, law enforcement officials, regulators, forensic experts and crypto industry leaders at the 3rd Annual Forum on AI & Crypto Fraud and Asset Recovery, taking place on 23–24 April 2026 at The Royal Horseguards Hotel in London  Part of C5 Group’s renowned Fraud & Asset Tracing Series, the Forum will deliver cutting-edge strategies to tackle crypto fraud, unlock asset […]

Ver mais

The AI Awards is accepting entries from companies worldwide working in AI. Those looking to submit their projects should do so before 19th of March 2026. The AI Awards has opened its 2026 call for entries, inviting organisations and individuals worldwide to submit their work across artificial intelligence applications. Set for 21 April in London, the event will gather professionals from data science, machine learning, automation, and applied AI sectors. The programme highlights projects, teams, and leaders whose […]

Ver mais

Magnetic resonance spectroscopy (MRS) is used to quantify metabolites in vivo and estimate biomarkers for conditions ranging from neurological disorders to cancers. Quantifying low-concentration metabolites such as GABA ($γ$-aminobutyric acid) is challenging due to low signal-to-noise ratio (SNR) and spectral overlap. We investigate and validate deep learning for quantifying complex, low-SNR, overlapping signals from MEGA-PRESS spectra, devise a convolutional neural network (CNN) and a Y-shaped autoencoder (YAE), and select the best models via Bayesian optimisation on 10,000 simulated […]

Ver mais

Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the increasing complexity of logistics networks, spanning multimodal transportation, cross-country routing, and pronounced regional variability, makes this prediction task inherently challenging. This paper introduces a multi-task deep learning model for delivery delay duration prediction in the presence of significant imbalanced data, where delayed shipments are rare but operationally consequential. The model embeds high-dimensional shipment features with dedicated embedding layers for […]

Ver mais

Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose machine learning framework that learns interpretable and identifiable optimization structures from data, ranging from single optimization problems to hierarchical compositions. It unifies predictive performance, intrinsic interpretability, and identifiability, with broad applicability to scientific domains involving optimization. BL parameterizes a compositional utility function built from intrinsically interpretable modular blocks, which induces a data distribution for prediction and generation. Each block represents and can be written in symbolic […]

Ver mais

Density functional theory (DFT) is the most widely used method for calculating molecular properties; however, its accuracy is often insufficient for quantitative predictions. Coupled-cluster (CC) theory is the most successful method for achieving accuracy beyond DFT and for predicting properties that closely align with experiment. It is known as the ”gold standard” of quantum chemistry. Unfortunately, the high computational cost of CC limits its widespread applicability. In this work, we present the Molecular Orbital Learning (MōLe) architecture, an […]

Ver mais

Ladybird adopts Rust, with help from AI Really interesting case-study from Andreas Kling on advanced, sophisticated use of coding agents for ambitious coding projects with critical code. After a few years hoping Swift’s platform support outside of the Apple ecosystem would mature they switched tracks to Rust their memory-safe language of choice, starting with an AI-assisted port of a critical library: Our first target was LibJS , Ladybird’s JavaScript engine. The lexer, parser, AST, and bytecode generator are […]

Ver mais