Breakthroughs, discoveries, and DIY tips sent every weekday.

The two images of Westerlund 2 show just how far the technology has come. Astronomers are studying the hundreds of young, brown dwarf stars inside the stellar nursery. Breakthroughs, discoveries, and DIY tips sent every weekday. In 2015, NASA celebrated the Hubble Space Telescope's 25th year in orbit by releasing one of its most stunning images to date--a colorful star cluster in the constellation Carina known as Westerlund 2 . However, a lot can change in a decade.

The evaluation of Vision-Language-Action (VLA) agents is hindered by the coarse, end-task success metric that fails to provide precise skill diagnosis or measure robustness to real-world perturbations. This challenge is exacerbated by a fragmented data landscape that impedes reproducible research and the development of generalist models. To address these limitations, we introduce NEBULA, a unified ecosystem for single-arm manipulation that enables diagnostic and reproducible evaluation. NEBULA features a novel dual-axis evaluation protocol that combines fine-grained capability tests for precise skill diagnosis with systematic stress tests that measure robustness. A standardized API and a large-scale, aggregated dataset are provided to reduce fragmentation and support cross-dataset training and fair comparison. Using NEBULA, we demonstrate that top-performing VLAs struggle with key capabilities such as spatial reasoning and dynamic adaptation, which are consistently obscured by conventional end-task success metrics. By measuring both what an agent can do and when it does so reliably, NEBULA provides a practical foundation for robust, general-purpose embodied agents.

The Gaia space observatory helped astronomers chart 4,000 light-years worth of our home galaxy. Against a black cosmic backdrop, countless white stars sparkle like scattered diamonds. Parts of the Milky Way's spiral arms are visible at the top of the image. Wisps of reddish-pink nebulas drift across the scene, forming delicate tendrils and cloud-like structures. Breakthroughs, discoveries, and DIY tips sent every weekday. A new 3D map can take you 4,000 light years from the sun-without leaving Earth.

We present NEBULA, the first latent 3D generative model for scalable generation of large molecular libraries around a seed compound of interest. Such libraries are crucial for scientific discovery, but it remains challenging to generate large numbers of high quality samples efficiently. 3D-voxel-based methods have recently shown great promise for generating high quality samples de novo from random noise (Pinheiro et al., 2023). However, sampling in 3D-voxel space is computationally expensive and use in library generation is prohibitively slow. Here, we instead perform neural empirical Bayes sampling (Saremi & Hyvarinen, 2019) in the learned latent space of a vector-quantized variational autoencoder. NEBULA generates large molecular libraries nearly an order of magnitude faster than existing methods without sacrificing sample quality. Moreover, NEBULA generalizes better to unseen drug-like molecules, as demonstrated on two public datasets and multiple recently released drugs. We expect the approach herein to be highly enabling for machine learning-based drug discovery. The code is available at https://github.com/prescient-design/nebula

When engaging in collaborative tasks, humans efficiently exploit the semantic structure of a conversation to optimize verbal and nonverbal interactions. But in recent "language to code" or "language to action" models, this information is lacking. We show how incorporating the prior discourse and nonlinguistic context of a conversation situated in a nonlinguistic environment can improve the "language to action" component of such interactions. We fine tune an LLM to predict actions based on prior context; our model, NeBuLa, doubles the net-action F1 score over the baseline on this task of Jayannavar et al.(2020). We also investigate our model's ability to construct shapes and understand location descriptions using a synthetic dataset.

Dynamic analysis enables detecting Windows malware by executing programs in a controlled environment, and storing their actions in log reports. Previous work has started training machine learning models on such reports to perform either malware detection or malware classification. However, most of the approaches (i) have only considered convolutional and long-short term memory networks, (ii) they have been built focusing only on APIs called at runtime, without considering other relevant though heterogeneous sources of information like network and file operations, and (iii) the code and pretrained models are hardly available, hindering reproducibility of results in this research area. In this work, we overcome these limitations by presenting Nebula, a versatile, self-attention transformer-based neural architecture that can generalize across different behavior representations and formats, combining heterogeneous information from dynamic log reports. We show the efficacy of Nebula on three distinct data collections from different dynamic analysis platforms, comparing its performance with previous state-of-the-art models developed for malware detection and classification tasks. We produce an extensive ablation study that showcases how the components of Nebula influence its predictive performance, while enabling it to outperform some competing approaches at very low false positive rates. We conclude our work by inspecting the behavior of Nebula through the application of explainability methods, which highlight that Nebula correctly focuses more on portions of reports that contain malicious activities. We release our code and models at github.com/dtrizna/nebula.

Open-source technologies have had a profound impact on the world of AI and machine learning, enabling developers, data scientists, and organizations to collaborate, innovate, and build better AI solutions. As large AI models like GPT-3.5 and DALL-E become more prevalent, organizations are also exploring ways to leverage existing open-source models and tools without needing to put a tremendous amount of effort into building them from scratch. Microsoft Azure AI is leading this effort by working closely with GitHub and data science communities, and providing organizations with access to a rich set of open-source technologies for building and deploying cutting-edge AI solutions. At Azure Open Source Day, we highlighted Microsoft's commitment to open source and how to build intelligent apps faster and with more flexibility using the latest open-source technologies that are available in Azure AI. Recent advancements in AI propelled the rise of large foundation models that are trained on a vast quantity of data and can be easily adapted to a wide variety of applications across various industries.

Data is eating the world and data centers rapidly expand to contain the more than 65 trillion gigabytes of data created and replicated worldwide. IDC predicts a 23% compound annual growth rate (CAGR) of data from 2020 to 2025, driving new applications and uses for AI or machine learning that is based on analysis of lots and lots of data. Such new AI applications are now reaching all corners of the corporate world, including the companies providing the tools, technologies, and infrastructure that are required for managing the data housed in large data centers. Google, for example, has used machine learning to find new ways to save energy in its data centers around the world, achieving in eighteen months a 40% reduction in energy used for cooling and 15% reduction in overall energy overhead. CDS, provider of multi-vendor services for data centers worldwide, today announced Nebula, a machine learning program that provides predictive intelligence on parts availability and delivery and other services for enhancing operations, sales, and service delivery.

Though NASA's Perseverance rover is on the Mars surface looking for signs of ancient life, the US space agency believes that robots looking in caves may help the US space agency find life outside this planet. As such, it is working with a number of contractors, including Boston Dynamics, on a project known as BRAILLE (Biologic and Resource Analog Investigations in Low Light Environments), exploring Mars-like caves on Earth in hopes that one day they will be used for future missions. Fully autonomous robots, like Boston Dynamics' Spot, could help explore these caves, which are believed to be hundreds of feet long and make communicating with Earth difficult, if not impossible. NASA is training robots like Boston Dynamics' Spot (pictured) to help traverse caves on Earth for future missions to Mars It is part of NASA's BRAILLE (Biologic and Resource Analog Investigations in Low Light Environments) project Fully autonomous robots could help explore Martian caves, believed to be hundreds of feet long. On Earth, NASA has incorporated its autonomy and artificial intelligence system, NeBula, into Spot, to help it explore the moon, Mars and other places in the solar system. 'Future potential human exploration missions can benefit from robots in many different ways,' Ali Agha, the project's research lead, told CBS News. 'Particularly, robots can be sent in precursor missions to provide more information about the destination before humans land on those destinations.