Coral reefs are rapidly declining due to anthropogenic pressures such as climate change, underscoring the urgent need for scalable, automated monitoring. We introduce ReefNet, a large public coral reef image dataset with point-label annotations mapped to the World Register of Marine Species (WoRMS). ReefNet aggregates imagery from 76 curated CoralNet sources and an additional site from Al Wajh in the Red Sea, totaling approximately 925000 genus-level hard coral annotations with expert-verified labels. Unlike prior datasets, which are often limited by size, geography, or coarse labels and are not ML-ready, ReefNet offers fine-grained, taxonomically mapped labels at a global scale to WoRMS. We propose two evaluation settings: (i) a within-source benchmark that partitions each source's images for localized evaluation, and (ii) a cross-source benchmark that withholds entire sources to test domain generalization. We analyze both supervised and zero-shot classification performance on ReefNet and find that while supervised within-source performance is promising, supervised performance drops sharply across domains, and performance is low across the board for zero-shot models, especially for rare and visually similar genera. This provides a challenging benchmark intended to catalyze advances in domain generalization and fine-grained coral classification. We will release our dataset, benchmarking code, and pretrained models to advance robust, domain-adaptive, global coral reef monitoring and conservation.

Large Language Models (LLMs) are rapidly being adopted in conservation to address the biodiversity crisis, yet their reliability for species evaluation is uncertain. This study systematically validates five leading models on 21,955 species across four core IUCN Red List assessment components: taxonomy, conservation status, distribution, and threats. A critical paradox was revealed: models excelled at taxonomic classification (94.9%) but consistently failed at conservation reasoning (27.2% for status assessment). This knowledge-reasoning gap, evident across all models, suggests inherent architectural constraints, not just data limitations. Furthermore, models exhibited systematic biases favoring charismatic vertebrates, potentially amplifying existing conservation inequities. These findings delineate clear boundaries for responsible LLM deployment: they are powerful tools for information retrieval but require human oversight for judgment-based decisions. A hybrid approach is recommended, where LLMs augment expert capacity while human experts retain sole authority over risk assessment and policy.

Recent advancements in Large Language Models (LLMs) have empowered LLM agents to autonomously collect world information, over which to conduct reasoning to solve complex problems. Given this capability, increasing interests have been put into employing LLM agents for predicting international events, which can influence decision-making and shape policy development on an international scale. Despite such a growing interest, there is a lack of a rigorous benchmark of LLM agents' forecasting capability and reliability. To address this gap, we introduce MIRAI, a novel benchmark designed to systematically evaluate LLM agents as temporal forecasters in the context of international events. Our benchmark features an agentic environment with tools for accessing an extensive database of historical, structured events and textual news articles. We refine the GDELT event database with careful cleaning and parsing to curate a series of relational prediction tasks with varying forecasting horizons, assessing LLM agents' abilities from short-term to long-term forecasting. We further implement APIs to enable LLM agents to utilize different tools via a code-based interface. In summary, MIRAI comprehensively evaluates the agents' capabilities in three dimensions: 1) autonomously source and integrate critical information from large global databases; 2) write codes using domain-specific APIs and libraries for tool-use; and 3) jointly reason over historical knowledge from diverse formats and time to accurately predict future events. Through comprehensive benchmarking, we aim to establish a reliable framework for assessing the capabilities of LLM agents in forecasting international events, thereby contributing to the development of more accurate and trustworthy models for international relation analysis.

Which specific insights are you interested in? I agree that IoT Analytics GmbH may process my information in accordance with its privacy statement to contact me and notify me of future research updates. Machine vision (MV) has the highest return on investment (ROI) and quickest amortization time of all Industry 4.0 technologies: For machine vision, this number is also among the lowest of all Industry 4.0 technologies. "In our latest project involving the implementation of an AI-based machine vision system for quality inspection of car assemblies, we achieved amortization in half a year." MV is the combination of different technologies and methods to automate the extraction of image information for providing operational guidance/key data for machines to execute a given task, in industrial and non-industrial settings.

Hannover Messe (or Hannover Fair), the #1 global industrial tradeshow, was back in action earlier this month. The event that took place from 30 May–02 June 2022, in Hannover, Germany, showcased once again the latest developments and industrial technology trends. Despite a much smaller crowd (75,000 visitors--roughly 40% of pre-pandemic levels), the fairgrounds were buzzing and filled with senior executives from many of the leading industrial hardware, software, and service providers. The conference remains one of those rare fairs where you randomly walk into senior executives, like a Head of Engineering for a major industrial conglomerate, and not only into the pre-sales representatives giving you the usual pitch. "In the face of disrupted supply chains, rising energy prices, inflation, and climate change, it was all the more important to meet face-to-face again in the exhibition halls after two years marked by a pandemic, to take in the latest technology trends and get a window to the future."

Large language models (LLMs) have rich internalized knowledge about the world and are able to carry out some degree of deduction and respond to questions requiring reasoning and inference. An example of ViLD object detection segmentation mask and bounding box predictions. The Inner Monologue system is created to chain together these components in a shared language prompt. As a result, the system can accomplish complex, long-horizon, and unseen tasks in simulation as well as on real-world robotic platforms. Recent works have shown how the reasoning capabilities of Large Language Models (LLMs) can be applied to domains beyond natural language processing, such as planning and interaction for robots.

A machine learning program has been used to distinguish between cancerous and healthy cells by identifying patterns in characteristic combinations of genes.

Current robot calibration techniques rely on specialized equipment and specially trained personnel. To overcome this problem, a recent paper published on arXiv.org It uses point cloud registration techniques to fuse multiple scans of a given scene. The evaluation on multiple real-world scenes on various hardware configurations shows that the achieved precision is similar to that achieved by using traditional methods with a dedicated 3D tracking system. Both, robot and hand-eye calibration haven been object to research for decades.

Understanding and manipulating articulated objects such as doors and drawers is a key skill for robots in human environments. However, it is difficult to train systems that generalize to variations of those objects. The sensory signal comes from an Azure Kinect depth camera, and the agent is a Sawyer BLACK robot. A novel per-point representation of the articulation structure of an object is proposed, called 3D Articulation Flow. A newly-developed 3D vision neural network architecture takes as input a static 3D point cloud and predicts the 3D Articulation Flow of the input under articulation motion.

SARS-CoV2, which causes coronavirus disease (COVID-19) is continuing to spread globally and has become a pandemic. People have lost their lives due to the virus and the lack of counter measures in place. Given the increasing caseload and uncertainty of spread, there is an urgent need to develop machine learning techniques to predict the spread of COVID-19. Prediction of the spread can allow counter measures and actions to be implemented to mitigate the spread of COVID-19. In this paper, we propose a deep learning technique, called Deep Sequential Prediction Model (DSPM) and machine learning based Non-parametric Regression Model (NRM) to predict the spread of COVID-19. Our proposed models were trained and tested on novel coronavirus 2019 dataset, which contains 19.53 Million confirmed cases of COVID-19. Our proposed models were evaluated by using Mean Absolute Error and compared with baseline method. Our experimental results, both quantitative and qualitative, demonstrate the superior prediction performance of the proposed models.