Deep learning models have shown encouraging capabilities for mapping accurately forests at medium resolution with TanDEM-X interferometric SAR data. Such models, as most of current state-of-the-art deep learning techniques in remote sensing, are trained in a fully-supervised way, which requires a large amount of labeled data for training and validation. In this work, our aim is to exploit the high-resolution capabilities of the TanDEM-X mission to map forests at 6 m. The goal is to overcome the intrinsic limitations posed by midresolution products, which affect, e.g., the detection of narrow roads within vegetated areas and the precise delineation of forested regions contours. To cope with the lack of extended reliable reference datasets at such a high resolution, we investigate self-supervised learning techniques for extracting highly informative representations from the input features, followed by a supervised training step with a significantly smaller number of reliable labels. A 1 m resolution forest/non-forest reference map over Pennsylvania, USA, allows for comparing different training approaches for the development of an effective forest mapping framework with limited labeled samples. We select the best-performing approach over this test region and apply it in a real-case forest mapping scenario over the Amazon rainforest, where only very few labeled data at high resolution are available. In this challenging scenario, the proposed self-supervised framework significantly enhances the classification accuracy with respect to fully-supervised methods, trained using the same amount of labeled data, representing an extremely promising starting point for large-scale, very high-resolution forest mapping with TanDEM-X data.

--We present the Inverse Drum Machine (IDM), a novel approach to Drum Source Separation that leverages an analysis-by-synthesis framework combined with deep learning. Unlike recent supervised methods that require isolated stem recordings, our approach operates on drum mixtures with only transcription annotations. IDM integrates Automatic Drum Transcription and One-shot drum Sample Synthesis, jointly optimizing these tasks in an end-to-end manner . By convolving synthesized one-shot samples with estimated onsets, akin to a drum machine, we reconstruct the individual drum stems and train a Deep Neural Network on the reconstruction of the mixture. Experiments on the StemGMD dataset demonstrate that IDM achieves separation quality comparable to state-of-the-art supervised methods that require isolated stems data, while significantly outperforming matrix decomposition baselines. N Western popular music, the rhythmic foundation typically relies on percussion instruments from a standard drum kit comprising kick drum, snare drum, and hi-hat, while additional elements such as cymbals, tom-toms, and auxiliary percussions provide timbral complexity and rhythmic variation. Music producers and engineers often need to adjust individual drum instruments separately for remixing, rebalanc-ing, effects processing, or creating educational materials [1], [2]. Ideally, music production would utilize isolated recordings of each drum instrument (known as "stems"), allowing for precise control during mixing. However, these instruments are usually played simultaneously and by the same performer, resulting in recordings in which all elements are mixed into a single audio stream. Obtaining these separated stems during recording requires multiple microphones (leading to microphone bleeding) or asking musicians to play in unnatural conditions [3]. The need for tools that can extract individual drum stems from already mixed recordings has led to growing interest in Drum Source Separation (DSS). These solutions, however, are proprietary and still have limitations in separation quality and flexibility. DSS is challenging due to the acoustic properties of percussion sounds.

Waves of Ukrainian drones have hit Moscow in recent days as the Russian capital prepares for the country's most important national holiday, Victory Day, this week. Russia celebrates May 9 as Victory Day to mark the defeat of Nazi forces in World War II. The day involves a major military parade, with leaders of Russia's allies often in attendance. But this year, the run-up to the day has been clouded by a warning from Ukrainian President Volodymyr Zelenskyy, who has said Kyiv cannot guarantee the safety of the foreign leaders attending the parade in Moscow. Here is more about Ukraine's attacks, Victory Day and why it is significant. Moscow Mayor Sergei Sobyanin said on Tuesday that Russia's air defence systems shot down 19 drones flying towards Moscow from different directions.

Russia has reported that it repelled a drone attack on Moscow as the capital city prepares to host a major military parade with foreign leaders in attendance. Russia's air defence systems intercepted "four drones flying towards Moscow", Mayor Sergei Sobyanin said on Monday. The attack appears intended to unsettle Moscow's preparations for events marking the end of the Great Patriotic War, commonly known as World War II elsewhere, on May 9. President Vladimir Putin has called for a 72-hour ceasefire to mark the occasion starting on May 8. However, Ukraine has demanded instead a 30-day truce aimed at agreeing to a permanent ceasefire in the conflict that began when Russia invaded in February 2022. Sobyanin said in a post on Telegram that there were no reports of injuries or damage.

Next Generation Reservoir Computing (NGRC) is a low-cost machine learning method for forecasting chaotic time series from data. However, ensuring the dynamical stability of NGRC models during autonomous prediction remains a challenge. In this work, we uncover a key connection between the numerical conditioning of the NGRC feature matrix -- formed by polynomial evaluations on time-delay coordinates -- and the long-term NGRC dynamics. Merging tools from numerical linear algebra and ergodic theory of dynamical systems, we systematically study how the feature matrix conditioning varies across hyperparameters. We demonstrate that the NGRC feature matrix tends to be ill-conditioned for short time lags and high-degree polynomials. Ill-conditioning amplifies sensitivity to training data perturbations, which can produce unstable NGRC dynamics. We evaluate the impact of different numerical algorithms (Cholesky, SVD, and LU) for solving the regularized least-squares problem.

--Background: As empirical software engineering evolves, more studies adopt data strategies--approaches that investigate digital artifacts such as models, source code, or system logs rather than relying on human subjects. Synthesizing results from such studies introduces new methodological challenges. Aims: This study assesses the effects of model quantization on correctness and resource efficiency in deep learning (DL) systems. Additionally, it explores the methodological implications of aggregating evidence from empirical studies that adopt data strategies. Method: We conducted a research synthesis of six primary studies that empirically evaluate model quantization. We applied the Structured Synthesis Method (SSM) to aggregate the findings, which combines qualitative and quantitative evidence through diagrammatic modeling. A total of 19 evidence models were extracted and aggregated. Results: The aggregated evidence indicates that model quantization weakly negatively affects correctness metrics while consistently improving resource efficiency metrics, including storage size, inference latency, and GPU energy consumption--a manageable trade-off for many DL deployment contexts. Evidence across quantization techniques remains fragmented, underscoring the need for more focused empirical studies per technique. Conclusions: Model quantization offers substantial efficiency benefits with minor trade-offs in correctness, making it a suitable optimization strategy for resource-constrained environments. This study also demonstrates the feasibility of using SSM to synthesize findings from data strategy-based research. Software engineering (SE) increasingly relies on data strategy studies [1] to understand and improve software development and deployment practices. Data strategies refer to "empirical studies that rely primarily on archival, generated or simulated data" [1], using a wide range of specific methods, including experiments and data mining studies. It is also partially funded by the Joan Or o pre-doctoral support program (BDNS 657443), co-funded by the European Union. Although these studies provide valuable information, they remain largely disconnected, with findings often limited to specific contexts and lacking broader theoretical integration. Therefore, the SE field struggles with few theories and needs more structured syntheses of existing research to guide future advancements.

The boss of the AI tool ChatGPT has revealed that his eyeball-scanning orbs are coming to the US, as questions still swirl around this dystopian step into the future. Sam Altman announced Wednesday that the identity verification technology will now be available in six cities - Atlanta, Austin, Los Angeles, Miami, Nashville, and San Francisco. The expansion into the US is all part of Altman's plan to create a new global identity and financial network. Currently, Altman's cryptocurrency company World has rolled out the orb devices in more than 35 cities across over 20 countries worldwide. The main purpose of these eyeball scanners is to verify that each user is a'unique human,' not a bot or duplicate account.

Proto-objects - image regions that share common visual properties - offer a promising alternative to traditional attention mechanisms based on rectangular-shaped image patches in neural networks. Although previous work demonstrated that evolving a patch-based hard-attention module alongside a controller network could achieve state-of-the-art performance in visual reinforcement learning tasks, our approach leverages image segmentation to work with higher-level features. By operating on proto-objects rather than fixed patches, we significantly reduce the representational complexity: each image decomposes into fewer proto-objects than regular patches, and each proto-object can be efficiently encoded as a compact feature vector. This enables a substantially smaller self-attention module that processes richer semantic information. Our experiments demonstrate that this proto-object-based approach matches or exceeds the state-of-the-art performance of patch-based implementations with 62% less parameters and 2.6 times less training time.

Racial disparities in healthcare expenditures are well-documented, yet the underlying drivers remain complex and require further investigation. This study employs causal and counterfactual path-specific effects to quantify how various factors, including socioeconomic status, insurance access, health behaviors, and health status, mediate these disparities. Using data from the Medical Expenditures Panel Survey, we estimate how expenditures would differ under counterfactual scenarios in which the values of specific mediators were aligned across racial groups along selected causal pathways. A key challenge in this analysis is ensuring robustness against model misspecification while addressing the zero-inflation and right-skewness of healthcare expenditures. For reliable inference, we derive asymptotically linear estimators by integrating influence function-based techniques with flexible machine learning methods, including super learners and a two-part model tailored to the zero-inflated, right-skewed nature of healthcare expenditures.

Despite the recent advances in Large Language Models, benchmarks for evaluating legal writing remain scarce due to the inherent complexity of assessing open-ended responses in this domain. One of the key challenges in evaluating language models on domain-specific tasks is finding test datasets that are public, frequently updated, and contain comprehensive evaluation guidelines. The Brazilian Bar Examination meets these requirements. We introduce oab-bench, a benchmark comprising 105 questions across seven areas of law from recent editions of the exam. The benchmark includes comprehensive evaluation guidelines and reference materials used by human examiners to ensure consistent grading. We evaluate the performance of four LLMs on oab-bench, finding that Claude-3.5 Sonnet achieves the best results with an average score of 7.93 out of 10, passing all 21 exams. We also investigated whether LLMs can serve as reliable automated judges for evaluating legal writing. Our experiments show that frontier models like OpenAI's o1 achieve a strong correlation with human scores when evaluating approved exams, suggesting their potential as reliable automated evaluators despite the inherently subjective nature of legal writing assessment. The source code and the benchmark -- containing questions, evaluation guidelines, model-generated responses, and their respective automated evaluations -- are publicly available.