New dinosaur discovered in Sahara desert was a horned'hell heron' 'Spinosaurus mirabilis' sported a 20-inch-tall'scimitar' on its head. Spinosaurus mirabilis stands along river's edge over its prey some 95 million years ago. A scimitar-shaped head crest and interdigitating teeth characterize this wading giant, one of the last-surviving spinosaurid species. Breakthroughs, discoveries, and DIY tips sent six days a week. Paleontologists still know comparatively little about fin-backed dinosaurs .

A new strain of mpox, previously called monkeypox, has been detected in a person in England, say UK health officials. The virus is a mix of two major types of the mpox virus, and was found in someone who recently returned from travelling in Asia. Officials say they are still assessing the significance of the new strain. The UK Health Security Agency (UKHSA) says it is normal for viruses to evolve. Getting vaccinated remains the best way to protect against severe disease - although an mpox infection is mild for many.

Large Language Models increasingly possess capabilities that carry dual-use risks. While data filtering has emerged as a pretraining-time mitigation, it faces significant challenges: labeling whether data is harmful is expensive at scale, and given improving sample efficiency with larger models, even small amounts of mislabeled content could give rise to dangerous capabilities. To address risks associated with mislabeled harmful content, prior work proposed Gradient Routing (Cloud et al., 2024) -- a technique that localizes target knowledge into a dedicated subset of model parameters so they can later be removed. We explore an improved variant of Gradient Routing, which we call Selective GradienT Masking (SGTM), with particular focus on evaluating its robustness to label noise. SGTM zero-masks selected gradients such that target domain examples only update their dedicated parameters. We test SGTM's effectiveness in two applications: removing knowledge of one language from a model trained on a bilingual synthetic dataset, and removing biology knowledge from a model trained on English Wikipedia. In both cases SGTM provides better retain/forget trade-off in the presence of labeling errors compared to both data filtering and a previously proposed instantiation of Gradient Routing. Unlike shallow unlearning approaches that can be quickly undone through fine-tuning, SGTM exhibits strong robustness to adversarial fine-tuning, requiring seven times more fine-tuning steps to reach baseline performance on the forget set compared to a finetuning-based unlearning method (RMU). Our results suggest SGTM provides a promising pretraining-time complement to existing safety mitigations, particularly in settings where label noise is unavoidable.

Resilient road infrastructure is a cornerstone of the UN Sustainable Development Goals. Yet a primary indicator of network functionality and resilience is critically lacking: a comprehensive global baseline of road surface information. Here, we overcome this gap by applying a deep learning framework to a global mosaic of Planetscope satellite imagery from 2020 and 2024. The result is the first global multi-temporal dataset of road pavedness and width for 9.2 million km of critical arterial roads, achieving 95.5% coverage where nearly half the network was previously unclassified. This dataset reveals a powerful multi-scale geography of human development. At the planetary scale, we show that the rate of change in pavedness is a robust proxy for a country's development trajectory (correlation with HDI = 0.65). At the national scale, we quantify how unpaved roads constitute a fragile backbone for economic connectivity. We further synthesize our data into a global Humanitarian Passability Matrix with direct implications for humanitarian logistics. At the local scale, case studies demonstrate the framework's versatility: in Ghana, road quality disparities expose the spatial outcomes of governance; in Pakistan, the data identifies infrastructure vulnerabilities to inform climate resilience planning. Together, this work delivers both a foundational dataset and a multi-scale analytical framework for monitoring global infrastructure, from the dynamics of national development to the realities of local governance, climate adaptation, and equity. Unlike traditional proxies such as nighttime lights, which reflect economic activity, road surface data directly measures the physical infrastructure that underpins prosperity and resilience - at higher spatial resolution.

Automated video analysis is critical for wildlife conservation. A foundational task in this domain is multi-animal tracking (MAT), which underpins applications such as individual re-identification and behavior recognition. However, existing datasets are limited in scale, constrained to a few species, or lack sufficient temporal and geographical diversity - leaving no suitable benchmark for training general-purpose MAT models applicable across wild animal populations. To address this, we introduce SA-FARI, the largest open-source MAT dataset for wild animals. It comprises 11,609 camera trap videos collected over approximately 10 years (2014-2024) from 741 locations across 4 continents, spanning 99 species categories. Each video is exhaustively annotated culminating in ~46 hours of densely annotated footage containing 16,224 masklet identities and 942,702 individual bounding boxes, segmentation masks, and species labels. Alongside the task-specific annotations, we publish anonymized camera trap locations for each video. Finally, we present comprehensive benchmarks on SA-FARI using state-of-the-art vision-language models for detection and tracking, including SAM 3, evaluated with both species-specific and generic animal prompts. We also compare against vision-only methods developed specifically for wildlife analysis. SA-FARI is the first large-scale dataset to combine high species diversity, multi-region coverage, and high-quality spatio-temporal annotations, offering a new foundation for advancing generalizable multianimal tracking in the wild. The dataset is available at https://www.conservationxlabs.com/sa-fari.

This paper investigates how individual entrepreneurs can turn creative ideas into successful solo businesses in an era increasingly shaped by Artificial Intelligence (AI) agents. It highlights the key steps that connect personal vision, structured experimentation, and lasting value creation, and shows how AI agents can act as digital co-founders throughout this journey. Building on research in entrepreneurship, creativity, and innovation, we present a framework with three key stages: (1) Imagination shaping, where vague goals become clear value propositions, supported by AI agents that help with market scanning, idea refinement, and rapid concept generation; (2) Reality testing, where these ideas are tested through low-cost experiments, structured feedback loops, and efficient execution, with AI agents automating tasks such as prototyping, content creation, customer interaction, and data analysis; and (3) Reality scaling, where successful ideas are transformed into repeatable processes, scalable market strategies, and long-term business models, increasingly operated and optimized by autonomous or semi-autonomous AI workflows. We focus on the specific context of solopreneurship, characterized by limited human resources, complete accountability for decision-making, and a strong association between the founder's identity and the business. The framework clearly identifies key enabling factors such as mental adaptability, effective planning, and successful human-AI collaboration within digital ecosystems. It also thoughtfully addresses ongoing challenges, like uncertainty and cognitive overload, which are heightened by our constant connectivity.

Speech technology remains out of reach for most of the over 2300 languages in Africa. We present the first systematic assessment of large-scale synthetic voice corpora for African ASR. We apply a three-step process: LLM-driven text creation, TTS voice synthesis, and ASR fine-tuning. Eight out of ten languages for which we create synthetic text achieved readability scores above 5 out of 7. We evaluated ASR improvement for three (Hausa, Dholuo, Chichewa) and created more than 2,500 hours of synthetic voice data at below 1% of the cost of real data. Fine-tuned Wav2Vec-BERT-2.0 models trained on 250h real and 250h synthetic Hausa matched a 500h real-data-only baseline, while 579h real and 450h to 993h synthetic data created the best performance. We also present gender-disaggregated ASR performance evaluation. For very low-resource languages, gains varied: Chichewa WER improved about 6.5% relative with a 1:2 real-to-synthetic ratio; a 1:1 ratio for Dholuo showed similar improvements on some evaluation data, but not on others. Investigating intercoder reliability, ASR errors and evaluation datasets revealed the need for more robust reviewer protocols and more accurate evaluation data. All data and models are publicly released to invite further work to improve synthetic data for African languages.

To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we present Global PIQA, a participatory commonsense reasoning benchmark for over 100 languages, constructed by hand by 335 researchers from 65 countries around the world. The 116 language varieties in Global PIQA cover five continents, 14 language families, and 23 writing systems. In the non-parallel split of Global PIQA, over 50% of examples reference local foods, customs, traditions, or other culturally-specific elements. We find that state-of-the-art LLMs perform well on Global PIQA in aggregate, but they exhibit weaker performance in lower-resource languages (up to a 37% accuracy gap, despite random chance at 50%). Open models generally perform worse than proprietary models. Global PIQA highlights that in many languages and cultures, everyday knowledge remains an area for improvement, alongside more widely-discussed capabilities such as complex reasoning and expert knowledge. Beyond its uses for LLM evaluation, we hope that Global PIQA provides a glimpse into the wide diversity of cultures in which human language is embedded.

Deep learning (DL)-based general circulation models (GCMs) are emerging as fast simulators, yet their ability to replicate extreme events outside their training range remains unknown. Here, we evaluate two such models -- the hybrid Neural General Circulation Model (NGCM) and purely data-driven Deep Learning Earth System Model (DL\textit{ESy}M) -- against a conventional high-resolution land-atmosphere model (HiRAM) in simulating land heatwaves and coldwaves. All models are forced with observed sea surface temperatures and sea ice over 1900-2020, focusing on the out-of-sample early-20th-century period (1900-1960). Both DL models generalize successfully to unseen climate conditions, broadly reproducing the frequency and spatial patterns of heatwave and cold wave events during 1900-1960 with skill comparable to HiRAM. An exception is over portions of North Asia and North America, where all models perform poorly during 1940-1960. Due to excessive temperature autocorrelation, DL\textit{ESy}M tends to overestimate heatwave and cold wave frequencies, whereas the physics-DL hybrid NGCM exhibits persistence more similar to HiRAM.

The ability to accurately align LLMs with human population groups on subjective questions would have great value. In this work, we show that use of simple supervision can greatly improve language model alignment with diverse population groups more consistently, as measured over three datasets spanning various topics. Beyond evaluating average alignment, we also report how alignment varies across specific groups. Our broad findings provide insights into the distributional alignment of LLMs with diverse population groups. By conducting evaluation over many LLMs and prompting strategies, along with open-sourcing our work, we provide a benchmark to stimulate future research.