In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are costly to store, difficult to evaluate for quality and balance, and pose privacy and ethical concerns due to the inclusion of sensitive information. Motivated by these limitations and risks, we propose an alternative training strategy where we leverage a collection of multiple, small-scale, and domain-specific datasets. We empirically demonstrate that the increased quality and diversity of such data improve the generalization abilities of in-context learners beyond their training domain, while achieving comparable performance with models trained on a single large-scale dataset. We investigate this paradigm by leveraging meta-learning to train an in-context learner on the Meta-Album collection under several settings. Firstly, we show the performance in a controlled environment, where the test domain is completely excluded from the training knowledge. Secondly, we explore the robustness of these models to forgetting in a continual scenario where the information is accessible for a limited time. Finally, we explore the more challenging unsupervised scenario. Our findings demonstrate that transformers still generalize for in-context prediction when trained on a curated dataset collection while offering advantages in modularity and replaceability.

We explore transfer learning strategies for musical onset detection in the Afro-Brazilian Maracatu tradition, which features complex rhythmic patterns that challenge conventional models. We adapt two Temporal Convolutional Network architectures: one pre-trained for onset detection (intra-task) and another for beat tracking (inter-task). Using only 5-second annotated snippets per instrument, we fine-tune these models through layer-wise retraining strategies for five traditional percussion instruments. Our results demonstrate significant improvements over baseline performance, with F1 scores reaching up to 0.998 in the intra-task setting and improvements of over 50 percentage points in best-case scenarios. The cross-task adaptation proves particularly effective for time-keeping instruments, where onsets naturally align with beat positions. The optimal fine-tuning configuration varies by instrument, highlighting the importance of instrument-specific adaptation strategies. This approach addresses the challenges of underrepresented musical traditions, offering an efficient human-in-the-loop methodology that minimizes annotation effort while maximizing performance. Our findings contribute to more inclusive music information retrieval tools applicable beyond Western musical contexts.

While continuous diffusion models excel in modeling continuous distributions, their application to categorical data has been less effective. Recent work has shown that ratio-matching through score-entropy within a continuous-time discrete Markov chain (CTMC) framework serves as a competitive alternative to autoregressive models in language modeling. To enhance this framework, we first introduce three new theorems concerning the KL divergence between the data and learned distribution. Our results serve as the discrete counterpart to those established for continuous diffusion models and allow us to derive an improved upper bound of the perplexity. Second, we empirically show that ratio-matching performed by minimizing the denoising cross-entropy between the clean and corrupted data enables models to outperform those utilizing score-entropy with up to 10% lower perplexity/generative-perplexity, and 15% faster training steps. To further support our findings, we introduce and evaluate a novel CTMC transition-rate matrix that allows prediction refinement, and derive the analytic expression for its matrix exponential which facilitates the computation of conditional ratios thus enabling efficient training and generation.

The ability to train Deep Neural Networks (DNNs) with constraints is instrumental in improving the fairness of modern machine-learning models. Many algorithms have been analysed in recent years, and yet there is no standard, widely accepted method for the constrained training of DNNs. In this paper, we provide a challenging benchmark of real-world large-scale fairness-constrained learning tasks, built on top of the US Census (Folktables). We point out the theoretical challenges of such tasks and review the main approaches in stochastic approximation algorithms. Finally, we demonstrate the use of the benchmark by implementing and comparing three recently proposed, but as-of-yet unimplemented, algorithms both in terms of optimization performance, and fairness improvement. We release the code of the benchmark as a Python package at https://github.com/humancompatible/train.

Theoretical works on supervised transfer learning (STL) -- where the learner has access to labeled samples from both source and target distributions -- have for the most part focused on statistical aspects of the problem, while efficient optimization has received less attention. We consider the problem of designing an SGD procedure for STL that alternates sampling between source and target data, while maintaining statistical transfer guarantees without prior knowledge of the quality of the source data. A main algorithmic difficulty is in understanding how to design such an adaptive sub-sampling mechanism at each SGD step, to automatically gain from the source when it is informative, or bias towards the target and avoid negative transfer when the source is less informative. We show that, such a mixed-sample SGD procedure is feasible for general prediction tasks with convex losses, rooted in tracking an abstract sequence of constrained convex programs that serve to maintain the desired transfer guarantees. We instantiate these results in the concrete setting of linear regression with square loss, and show that the procedure converges, with $1/\sqrt{T}$ rate, to a solution whose statistical performance on the target is adaptive to the a priori unknown quality of the source. Experiments with synthetic and real datasets support the theory.

This paper presents ``randomized SINDy", a sequential machine learning algorithm designed for dynamic data that has a time-dependent structure. It employs a probabilistic approach, with its PAC learning property rigorously proven through the mathematical theory of functional analysis. The algorithm dynamically predicts using a learned probability distribution of predictors, updating weights via gradient descent and a proximal algorithm to maintain a valid probability density. Inspired by SINDy (Brunton et al. 2016), it incorporates feature augmentation and Tikhonov regularization. For multivariate normal weights, the proximal step is omitted to focus on parameter estimation. The algorithm's effectiveness is demonstrated through experimental results in regression and binary classification using real-world data.

Recent studies in the spatial prisoner's dilemma games with reinforcement learning have shown that static agents can learn to cooperate through a diverse sort of mechanisms, including noise injection, different types of learning algorithms and neighbours' payoff knowledge. In this work, using an independent multi-agent Q-learning algorithm, we study the effects of dilution and mobility in the spatial version of the prisoner's dilemma. Within this setting, different possible actions for the algorithm are defined, connecting with previous results on the classical, non-reinforcement learning spatial prisoner's dilemma, showcasing the versatility of the algorithm in modeling different game-theoretical scenarios and the benchmarking potential of this approach. As a result, a range of effects is observed, including evidence that games with fixed update rules can be qualitatively equivalent to those with learned ones, as well as the emergence of a symbiotic mutualistic effect between populations that forms when multiple actions are defined.

SOLVA Archaeology Service in Belgium announced the recent discovery of ancient Roman artifacts and remains, including a well-preserved dog, in Velzeke. A remarkable medieval sword with rare symbols was recently put on display in a Dutch museum, over a year after it was found by construction workers unexpectedly. The discovery of the sword was announced by the Netherlands' National Museum of Antiquities (RMO) in Leiden on June 24. The artifact, named the Linschoten Sword, was found in March 2024 during "maintenance dredging activities," the museum said in a press release. Construction workers were struck by a "long piece of iron" while cleaning a small river known as the Korte Linschoten, the statement noted.

Here are the key events on day 1,226 of Russia's war on Ukraine.Smoke is seen following what local authorities called a Ukrainian drone attack, in the course of Russia-Ukraine conflict, in Sergiyev Posad, outside Moscow, Russia July 4, 2025 [Head of the Sergiyev Posad municipal district Oksana Yerokhanova via Telegram/Handout via Reuters]Published On 4 Jul 20254 Jul 2025

The emergence of Open Banking represents a significant shift in financial data management, influencing financial institutions' market dynamics and marketing strategies. This increased competition creates opportunities and challenges, as institutions manage data inflow to improve products and services while mitigating data outflow that could aid competitors. This study introduces a framework to predict customers' propensity to share data via Open Banking and interprets this behavior through Explanatory Model Analysis (EMA). Using data from a large Brazilian financial institution with approximately 3.2 million customers, a hybrid data balancing strategy incorporating ADASYN and NEARMISS techniques was employed to address the infrequency of data sharing and enhance the training of XGBoost models. These models accurately predicted customer data sharing, achieving 91.39% accuracy for inflow and 91.53% for outflow. The EMA phase combined the Shapley Additive Explanations (SHAP) method with the Classification and Regression Tree (CART) technique, revealing the most influential features on customer decisions. Key features included the number of transactions and purchases in mobile channels, interactions within these channels, and credit-related features, particularly credit card usage across the national banking system. These results highlight the critical role of mobile engagement and credit in driving customer data-sharing behaviors, providing financial institutions with strategic insights to enhance competitiveness and innovation in the Open Banking environment.