Search

Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage representations to support few-shot adaptation. In this work, we propose a simple, but carefully designed extension to multimodal pretraining which enables representations to accommodate additional context. Using this objective, we show that vision-language models can be trained to exhibit significantly increased few-shot adaptation: across 21 downstream tasks, we find up to four-fold improvements in test-time sample efficiency, and average few-shot adaptation gains of over 5%, while retaining zero-shot generalization performance across model scales and training durations. In particular, equipped with simple, training-free, metric-based adaptation mechanisms, our representations easily surpass more complex and expensive optimization-based schemes, vastly simplifying generalization to new domains.

Coupled decompositions are a widely used tool for data fusion. This paper studies the coupled matrix factorization (CMF) where two matrices $X$ and $Y$ are represented in a low-rank format sharing one common factor, as well as the coupled matrix and tensor factorization (CMTF) where a matrix $Y$ and a tensor $\mathcal{X}$ are represented in a low-rank format sharing a factor matrix. We show that these problems are equivalent to the low-rank approximation of the matrix $[X \ Y]$ for CMF, that is $[X_{(1)} \ Y]$ for CMTF. Then, in order to speed up computation process, we adapt several randomization techniques, namely, randomized SVD, randomized subspace iteration, and randomized block Krylov iteration to the algorithms for coupled decompositions. We present extensive results of the numerical tests. Furthermore, as a novel approach and with a high success rate, we apply our randomized algorithms to the face recognition problem., Comment: 25 pages, 11 figures, 7 tables

The abilities of traditional perimeter-based security architectures are rapidly decreasing as more enterprise assets are moved toward the cloud environment. From a security viewpoint, the Zero Trust framework can better track and block external attackers while limiting security breaches resulting from insider attacks in the cloud paradigm. Furthermore, Zero Trust can better accomplish access privileges for users and devices across cloud environments to enable the secure sharing of resources. Moreover, the concept of zero trust architecture in cloud computing requires the integration of complex practices on multiple layers of system architecture, as well as a combination of a variety of existing technologies. This paper focuses on authentication mechanisms, calculation of trust score, and generation of policies in order to establish required access control to resources. The main objective is to incorporate an unbiased trust score as a part of policy expressions while preserving the configurability and adaptiveness of parameters of interest. Finally, the proof-of-concept is demonstrated on a micro-cloud plat-form solution., Comment: 10 pages, 2 figures

The immense shift to cloud computing has brought changes in security and privacy requirements, impacting critical Identity Management services. Currently, many IdM systems and solutions are accessible as cloud services, delivering identity services for applications in closed domains and the public cloud. This research paper centres on identity management in distributed environments, emphasising the importance of robust up to date authorisation mechanisms. The paper concentrates on implementing robust security paradigms to minimise communication overhead among services while preserving privacy and access control. The key contribution focuses on solving the problem of restricted access to resources in cases when the authentication token is still valid, but permissions are updated. The proposed solution incorporates an Identity and Access Management server as a component that authenticates all external requests. The IAM server key responsibilities include maintaining user data, assigning privileges within the system, and authorisation. Furthermore, it empowers users by offering an Application Programming Interface for managing users and their rights within the same organisation, providing finer granularity in authorisation. The IAM server has been integrated with a configuration dissemination tool designed as a distributed cloud infrastructure to evaluate the solution., Comment: 10 pages, 2 figures

Estimated brain age from magnetic resonance image (MRI) and its deviation from chronological age can provide early insights into potential neurodegenerative diseases, supporting early detection and implementation of prevention strategies. Diffusion MRI (dMRI), a widely used modality for brain age estimation, presents an opportunity to build an earlier biomarker for neurodegenerative disease prediction because it captures subtle microstructural changes that precede more perceptible macrostructural changes. However, the coexistence of macro- and micro-structural information in dMRI raises the question of whether current dMRI-based brain age estimation models are leveraging the intended microstructural information or if they inadvertently rely on the macrostructural information. To develop a microstructure-specific brain age, we propose a method for brain age identification from dMRI that minimizes the model's use of macrostructural information by non-rigidly registering all images to a standard template. Imaging data from 13,398 participants across 12 datasets were used for the training and evaluation. We compare our brain age models, trained with and without macrostructural information minimized, with an architecturally similar T1-weighted (T1w) MRI-based brain age model and two state-of-the-art T1w MRI-based brain age models that primarily use macrostructural information. We observe difference between our dMRI-based brain age and T1w MRI-based brain age across stages of neurodegeneration, with dMRI-based brain age being older than T1w MRI-based brain age in participants transitioning from cognitively normal (CN) to mild cognitive impairment (MCI), but younger in participants already diagnosed with Alzheimer's disease (AD). Approximately 4 years before MCI diagnosis, dMRI-based brain age yields better performance than T1w MRI-based brain ages in predicting transition from CN to MCI.

Owing to their cost-effectiveness and flexibility, cloud services have been the default choice for the deployment of innumerable software systems over the years. However, novel paradigms are beginning to emerge, as the cloud can't meet the requirements of increasingly many latency- and privacy-sensitive applications. The distributed cloud model, being one of the attempts to overcome these challenges, places a distributed cloud layer between device and cloud layers, intending to bring resources closer to data sources. As application code should be kept separate from its configuration, especially in highly dynamic cloud environments, there is a need to incorporate configuration primitives in future distributed cloud platforms. In this paper, we present the design and implementation of a configuration management subsystem for an open-source distributed cloud platform. Our solution spreads across the cloud and distributed cloud layers and supports configuration versioning, selective dissemination to nodes in the distributed cloud layer, and logical isolation via namespaces. Our work serves as a demonstration of the feasibility and usability of the new cloud-extending models and provides valuable insight into one of the possible implementations.

Preclinical diffusion MRI (dMRI) has proven value in methods development and validation, characterizing the biological basis of diffusion phenomena, and comparative anatomy. While dMRI enables in vivo non-invasive characterization of tissue, ex vivo dMRI is increasingly being used to probe tissue microstructure and brain connectivity. Ex vivo dMRI has several experimental advantages that facilitate high spatial resolution and high signal-to-noise ratio (SNR) images, cutting-edge diffusion contrasts, and direct comparison with histological data as a methodological validation. However, there are a number of considerations that must be made when performing ex vivo experiments. The steps from tissue preparation, image acquisition and processing, and interpretation of results are complex, with many decisions that not only differ dramatically from in vivo imaging of small animals, but ultimately affect what questions can be answered using the data. This work concludes a 3-part series of recommendations and considerations for preclinical dMRI. Herein, we describe best practices for dMRI of ex vivo tissue, with a focus on image pre-processing, data processing and model fitting, and tractography. In each section, we attempt to provide guidelines and recommendations, but also highlight areas for which no guidelines exist (and why), and where future work should lie. We end by providing guidelines on code sharing and data sharing, and point towards open-source software and databases specific to small animal and ex vivo imaging., Comment: Part 3 of 3 in "Considerations and recommendations for preclinical diffusion MRI"

Dynamic scheduling of access to shared resources by autonomous systems is a challenging problem, characterized as being NP-hard. The complexity of this task leads to a combinatorial explosion of possibilities in highly dynamic systems where arriving requests must be continuously scheduled subject to strong safety and time constraints. An example of such a system is an unsignalized intersection, where automated vehicles' access to potential conflict zones must be dynamically scheduled. In this paper, we apply Neural Monte Carlo Tree Search (NMCTS) to the challenging task of scheduling platoons of vehicles crossing unsignalized intersections. Crucially, we introduce a transformation model that maps successive sequences of potentially conflicting road-space reservation requests from platoons of vehicles into a series of board-game-like problems and use NMCTS to search for solutions representing optimal road-space allocation schedules in the context of past allocations. To optimize search, we incorporate a prioritized re-sampling method with parallel NMCTS (PNMCTS) to improve the quality of training data. To optimize training, a curriculum learning strategy is used to train the agent to schedule progressively more complex boards culminating in overlapping boards that represent busy intersections. In a busy single four-way unsignalized intersection simulation, PNMCTS solved 95\% of unseen scenarios, reducing crossing time by 43\% in light and 52\% in heavy traffic versus first-in, first-out control. In a 3x3 multi-intersection network, the proposed method maintained free-flow in light traffic when all intersections are under control of PNMCTS and outperformed state-of-the-art RL-based traffic-light controllers in average travel time by 74.5\% and total throughput by 16\% in heavy traffic.

Direct air capture (DAC) of carbon dioxide is a critical technology for mitigating climate change, but current materials face limitations in efficiency and scalability. We discover novel DAC materials using a combined machine learning (ML) and high-throughput atomistic modeling approach. Our ML model accurately predicts high-quality, density functional theory-computed CO$_{2}$ binding enthalpies for a wide range of nitrogen-bearing moieties. Leveraging this model, we rapidly screen over 1.6 million binding sites from a comprehensive database of theoretically feasible molecules to identify materials with superior CO$_{2}$ binding properties. Additionally, we assess the synthesizability and experimental feasibility of these structures using established ML metrics, discovering nearly 2,500 novel materials suitable for integration into DAC devices. Altogether, our high-fidelity database and ML framework represent a significant advancement in the rational development of scalable, cost-effective carbon dioxide capture technologies, offering a promising pathway to meet key targets in the global initiative to combat climate change., Comment: 18 pages, 6 figures

In crystalline materials, low lattice thermal conductivity is often associated with strong anharmonicity, which can cause significant deviations from the expected Lorentzian lineshape of phonon spectral functions. These deviations, occurring in an overdamped regime, raise questions about the applicability of the Boltzmann transport equation. Furthermore, strong anharmonicity can trigger structural phase transitions with temperature, which cannot be adequately described by the standard harmonic approximation. To address these challenges, we propose a novel approach for computing the lattice thermal conductivity. Our method combines the Green-Kubo linear response theory with the stochastic self-consistent harmonic approximation. The latter allows us to describe the temperature-dependent evolution of the crystal structure, including first- and second-order phase transitions, as well as the vibrational properties in highly anharmonic materials. The Green-Kubo method considers the entire lineshapes of phonon spectral functions in the calculation of the lattice thermal conductivity, thus eliminating the questionable use of phonon lifetimes in the overdamped regime, as well as naturally including coherent transport effects. Additionally, we extend our theory to model complex dynamical lattice thermal conductivity, enhancing our understanding of time-dependent thermoreflectance experiments. As a practical application, we employ this approach to calculate the lattice thermal conductivity of CsPbBr$_3$, a complex crystal known for its anomalous thermal transport behavior with a complex phase diagram. Our method is able to determine the thermal conductivity across different phases in good agreement with experiments.

Neutral atom quantum processors are a promising platform for large-scale quantum computing. Integrating them with an optical cavity enables fast nondestructive qubit readout and access to fast remote entanglement generation for quantum networking. Here, we introduce a platform for coupling single atoms in optical tweezers to a Fabry-Perot Fiber Cavity. Leveraging the strong atom-cavity coupling, we demonstrate fast qubit state readout with 99.960$^{+14}_{-24}\%$ fidelity and two methods for cavity-mediated entanglement generation with integrated error detection. First, we use cavity-carving to generate a Bell state with 91(4)$\%$ fidelity and a 32(1)$\%$ success rate. Second, we perform a cavity-mediated gate with a deterministic entanglement fidelity of 52.5(18)$\%$, increased to 76(2)$\%$ with error detection. The new capabilities enabled by this platform pave the way towards modular quantum computing and networking.

Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often demands complex and deep architectures, which are expensive to compute and train. Within the world model, dynamics models are particularly crucial for accurate predictions, and various dynamics-model architectures have been explored, each with its own set of challenges. Currently, recurrent neural network (RNN) based world models face issues such as vanishing gradients and difficulty in capturing long-term dependencies effectively. In contrast, use of transformers suffers from the well-known issues of self-attention mechanisms, where both memory and computational complexity scale as $O(n^2)$, with $n$ representing the sequence length. To address these challenges we propose a state space model (SSM) based world model, specifically based on Mamba, that achieves $O(n)$ memory and computational complexity while effectively capturing long-term dependencies and facilitating the use of longer training sequences efficiently. We also introduce a novel sampling method to mitigate the suboptimality caused by an incorrect world model in the early stages of training, combining it with the aforementioned technique to achieve a normalised score comparable to other state-of-the-art model-based RL algorithms using only a 7 million trainable parameter world model. This model is accessible and can be trained on an off-the-shelf laptop. Our code is available at https://github.com/realwenlongwang/drama.git.

Dense cold molecular cores/filaments are surrounded by an envelope of translucent gas. Some of the low-J emission lines of CO and HCO$^+$ isotopologues are more sensitive to the conditions either in the translucent environment or in the dense cold one. We propose a cloud model composed of three homogeneous slabs of gas along each line of sight (LoS), representing an envelope and a shielded inner layer. IRAM-30m data from the ORION-B large program toward the Horsehead nebula are used to demonstrate the method's capability. We use the non-LTE radiative transfer code RADEX to model the line profiles from the kinetic temperature $T_{kin}$, the volume density $n_{H_2}$, kinematics and chemical properties of the different layers. We then use a maximum likelihood estimator to simultaneously fit the lines of the CO and HCO$^+$ isotopologues. We constrain column density ratios to limit the variance on the estimates. This simple heterogeneous model provides good fits of the fitted lines over a large part of the cloud. The decomposition of the intensity into three layers allows to discuss the distribution of the estimated physical/chemical properties along the LoS. About 80$\%$ the CO integrated intensity comes from the envelope, while $\sim55\%$ of that of the (1-0) and (2-1) lines of C$^{18}$O comes from the inner layer. The $N(^{13}CO)/N(C^{18}O)$ in the envelope increases with decreasing $A_v$, and reaches $25$ in the pillar outskirts. The envelope $T_{kin}$ varies from 25 to 40 K, that of the inner layer drops to $\sim 15$ K in the western dense core. The inner layer $n_{H_2}$ is $\sim 3\times10^4\,\text{cm}^{-3}$ toward the filament and it increases by a factor $10$ toward dense cores. The proposed method correctly retrieves the physical/chemical properties of the Horsehead nebula and offers promising prospects for less supervised model fits of wider-field datasets.

We report the first successful ALMA follow-up observations of a secure $z > 10$ JWST-selected galaxy, by robustly detecting ($6.6\sigma$) the [OIII]$_{88\mu m}\,$ line in JADES-GS-z14-0 (hereafter GS-z14). The ALMA detection yields a spectroscopic redshift of $z=14.1793\pm0.0007$, and increases the precision on the prior redshift measurement of $z=14.32_{-0.20}^{+0.08}$ from NIRSpec by $\gtrsim$180$\times$. Moreover, the redshift is consistent with that previously determined from a tentative detection ($3.6\sigma$) of CIII]$_{1907,1909}$ ($z=14.178\pm0.013$), solidifying the redshift determination via multiple line detections. We measure a line luminosity of $L_\mathrm{[OIII]88} = (2.1 \pm 0.5)\times10^8\,L_\odot$, placing GS-z14 at the lower end, but within the scatter of, the local $L_\mathrm{[OIII]88}$-star formation rate relation. No dust continuum from GS-z14 is detected, suggesting an upper limit on the dust-to-stellar mass ratio of $< 2 \times 10^{-3}$, consistent with dust production from supernovae with a yield $y_d < 0.3\,M_\odot$. Combining a previous JWST/MIRI photometric measurement of the [OIII]$\lambda\lambda$4959,5007$\mathrm{\mathring{A}}$ and H$\beta$ lines with Cloudy models, we find GS-z14 to be surprisingly metal-enriched ($Z\sim0.05 - 0.2\,Z_\odot$) a mere $300\,\mathrm{Myr}$ after the Big Bang. The detection of a bright oxygen line in GS-z14 thus reinforces the notion that galaxies in the early Universe undergo rapid evolution., Comment: 11 Pages, 6 Figures, 1 Table. Submitted to The Astrophysical Journal

Objective: To propose a mathematical model for applying Ionization Detail (ID), the detailed spatial distribution of ionization along a particle track, to proton and ion beam radiotherapy treatment planning (RTP). Approach: Our model provides for selection of preferred ID parameters (I_p) for RTP, that associate closest to biological effects. Cluster dose is proposed to bridge the large gap between nanoscopic I_p and macroscopic RTP. Selection of I_p is demonstrated using published cell survival measurements for protons through argon, comparing results for nineteen Ip: N_k; k = 2,3,...,10, the number of ionizations in clusters of k or more per particle, and F_k; k = 1,2,...,10, the number of clusters of k or more per particle. We then describe application of the model to ID-based RTP and propose a path to clinical translation. Main results: The preferred I_p were N_4 and F_5 for aerobic cells, N_5 and F_7 for hypoxic cells. Signifcant differences were found in cell survival for beams having the same LET or the preferred N_k. Conversely, there was no signi?cant difference for F_5 for aerobic cells and F_7 for hypoxic cells, regardless of ion beam atomic number or energy. Further, cells irradiated with the same cluster dose for these I_p had the same cell survival. Based on these preliminary results and other compelling results in nanodosimetry, it is reasonable to assert that I_p exist that are more closely associated with biological effects than current LET-based approaches and microdosimetric RBE-based models used in particle RTP. However, more biological variables such as cell line and cycle phase, as well as ion beam pulse structure and rate still need investigation. Signifcance: Our model provides a practical means to select preferred I_p from radiobiological data, and to convert I_p to the macroscopic cluster dose for particle RTP., Comment: 31 pages, 12 figures

Deep learning-based medical image segmentation and surface mesh generation typically involve a sequential pipeline from image to segmentation to meshes, often requiring large training datasets while making limited use of prior geometric knowledge. This may lead to topological inconsistencies and suboptimal performance in low-data regimes. To address these challenges, we propose a data-efficient deep learning method for direct 3D anatomical object surface meshing using geometric priors. Our approach employs a multi-resolution graph neural network that operates on a prior geometric template which is deformed to fit object boundaries of interest. We show how different templates may be used for the different surface meshing targets, and introduce a novel masked autoencoder pretraining strategy for 3D spherical data. The proposed method outperforms nnUNet in a one-shot setting for segmentation of the pericardium, left ventricle (LV) cavity and the LV myocardium. Similarly, the method outperforms other lumen segmentation operating on multi-planar reformatted images. Results further indicate that mesh quality is on par with or improves upon marching cubes post-processing of voxel mask predictions, while remaining flexible in the choice of mesh triangulation prior, thus paving the way for more accurate and topologically consistent 3D medical object surface meshing., Comment: Submitted to Medical Image Analysis

We present a comprehensive dataset of Java vulnerability-fixing commits (VFCs) to advance research in Java vulnerability analysis. Our dataset, derived from thousands of open-source Java projects on GitHub, comprises two variants: JavaVFC and JavaVFC-extended. The dataset was constructed through a rigorous process involving heuristic rules and multiple rounds of manual labeling. We initially used keywords to filter candidate VFCs based on commit messages, then refined this keyword set through iterative manual labeling. The final labeling round achieved a precision score of 0.7 among three annotators. We applied the refined keyword set to 34,321 open-source Java repositories with over 50 GitHub stars, resulting in JavaVFC with 784 manually verified VFCs and JavaVFC-extended with 16,837 automatically identified VFCs. Both variants are presented in a standardized JSONL format for easy access and analysis. This dataset supports various research endeavors, including VFC identification, fine-grained vulnerability detection, and automated vulnerability repair. The JavaVFC and JavaVFC-extended are publicly available at https://zenodo.org/records/13731781.

Reinforcement Learning (RL) is a learning paradigm in which the agent learns from its environment through trial and error. Deep reinforcement learning (DRL) algorithms represent the agent's policies using neural networks, making their decisions difficult to interpret. Explaining the behaviour of DRL agents is necessary to advance user trust, increase engagement, and facilitate integration with real-life tasks. Semifactual explanations aim to explain an outcome by providing "even if" scenarios, such as "even if the car were moving twice as slowly, it would still have to swerve to avoid crashing". Semifactuals help users understand the effects of different factors on the outcome and support the optimisation of resources. While extensively studied in psychology and even utilised in supervised learning, semifactuals have not been used to explain the decisions of RL systems. In this work, we develop a first approach to generating semifactual explanations for RL agents. We start by defining five properties of desirable semifactual explanations in RL and then introducing SGRL-Rewind and SGRL-Advance, the first algorithms for generating semifactual explanations in RL. We evaluate the algorithms in two standard RL environments and find that they generate semifactuals that are easier to reach, represent the agent's policy better, and are more diverse compared to baselines. Lastly, we conduct and analyse a user study to assess the participant's perception of semifactual explanations of the agent's actions., Comment: 9 pages, 2 figures, 4 tables

The radial gradient of gas-phase metallicity is a powerful probe of the chemical and structural evolution of star-forming galaxies, closely tied to disk formation and gas kinematics in the early universe. We present spatially resolved chemical and dynamical properties for a sample of 26 galaxies at $0.5 \lesssim z \lesssim 1.7$ from the MSA-3D survey. These innovative observations provide 3D spectroscopy of galaxies at a spatial resolution approaching JWST's diffraction limit and a high spectral resolution of $R\simeq2700$. The metallicity gradients measured in our galaxy sample range from $-$0.05 to 0.02 dex~kpc$^{-1}$. Most galaxies exhibit negative or flat radial gradients, indicating lower metallicity in the outskirts or uniform metallicity throughout the entire galaxy. We confirm a tight relationship between stellar mass and metallicity gradient at $z\sim1$ with small intrinsic scatter of 0.02 dex~kpc$^{-1}$. Our results indicate that metallicity gradients become increasingly negative as stellar mass increases, likely because the more massive galaxies tend to be more "disky". This relationship is consistent with the predictions from cosmological hydrodynamic zoom-in simulations with strong stellar feedback. This work presents the effort to harness the multiplexing capability of JWST NIRSpec/MSA in slit-stepping mode to map the chemical and kinematic profiles of high-redshift galaxies in large samples and at high spatial and spectral resolution., Comment: 23 pages, 6 figures, 1 table; submitted to ApJL

This study investigates the ability of various vision-language (VL) models to ground context-dependent and non-context-dependent verb phrases. To do that, we introduce the CV-Probes dataset, designed explicitly for studying context understanding, containing image-caption pairs with context-dependent verbs (e.g., "beg") and non-context-dependent verbs (e.g., "sit"). We employ the MM-SHAP evaluation to assess the contribution of verb tokens towards model predictions. Our results indicate that VL models struggle to ground context-dependent verb phrases effectively. These findings highlight the challenges in training VL models to integrate context accurately, suggesting a need for improved methodologies in VL model training and evaluation., Comment: 13 pages, 1 figure, 11 tables, LIMO Workshop at KONVENS 2024

Integral field spectroscopy (IFS) is a powerful tool for understanding the formation of galaxies across cosmic history. We present the observing strategy and first results of MSA-3D, a novel JWST program using multi-object spectroscopy in a slit-stepping strategy to produce IFS data cubes. The program observed 43 normal star-forming galaxies at redshifts $0.5 \lesssim z \lesssim 1.5$, corresponding to the epoch when spiral thin-disk galaxies of the modern Hubble sequence are thought to emerge, obtaining kpc-scale maps of rest-frame optical nebular emission lines with spectral resolution $R\simeq2700$. Here we describe the multiplexed slit-stepping method which is $>15$ times more efficient than the NIRSpec IFS mode for our program. As an example of the data quality, we present a case study of an individual galaxy at $z=1.104$ (stellar mass $M_{*} = 10^{10.3}~M_{\odot}$, star formation rate~$=3~M_{\odot}$ yr$^{-1}$) with prominent face-on spiral structure. We show that the galaxy exhibits a rotationally supported disk with moderate velocity dispersion ($\sigma = 36^{+5}_{-4}$~\kms), a negative radial metallicity gradient ($-0.020\pm0.002$~dex\,kpc$^{-1}$), a dust attenuation gradient, and an exponential star formation rate density profile which closely matches the stellar continuum. These properties are characteristic of local spirals, indicating that mature galaxies are in place at $z\sim1$. We also describe the customized data reduction and original cube-building software pipelines which we have developed to exploit the powerful slit-stepping technique. Our results demonstrate the ability of JWST slit-stepping to study galaxy populations at intermediate to high redshifts, with data quality similar to current surveys of the $z\sim0.1$ universe., Comment: 24 pages, 12 figures, 1 table; submitted to ApJ, comments welcome. Our custom designed data reduction pipeline (MSA3D) and example processed data-cube will be publicly released before the JWST Cycle 4 deadline. MSA3D package on GitHub: https://github.com/barisiciv/msa3d.git

Observations of ionic, atomic, or molecular lines are performed to improve our understanding of the interstellar medium (ISM). However, the potential of a line to constrain the physical conditions of the ISM is difficult to assess quantitatively, because of the complexity of the ISM physics. The situation is even more complex when trying to assess which combinations of lines are the most useful. Therefore, observation campaigns usually try to observe as many lines as possible for as much time as possible. We search for a quantitative statistical criterion to evaluate the constraining power of a (or combination of) tracer(s) with respect to physical conditions in order to improve our understanding of the statistical relationships between ISM tracers and physical conditions and helps observers to motivate their observation proposals. The best tracers are obtained by comparing the mutual information between a physical parameter and different sets of lines. We apply this method to simulations of radio molecular lines emitted by a photodissociation region similar to the Horsehead Nebula that would be observed at the IRAM 30m telescope. We search for the best lines to constrain the visual extinction $A_v^{tot}$ or the far UV illumination $G_0$. The most informative lines change with the physical regime (e.g., cloud extinction). Short integration time of the CO isotopologue $J=1-0$ lines already yields much information on the total column density most regimes. The best set of lines to constrain the visual extinction does not necessarily combine the most informative individual lines. Precise constraints on $G_0$ are more difficult to achieve with molecular lines. They require spectral lines emitted at the cloud surface (e.g., [CII] and [CI] lines). This approach allows one to better explore the knowledge provided by ISM codes, and to guide future observation campaigns.

We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred over other state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss issues around safety and representation, as well as methods we used to minimize the potential harm of our models.

The field of single-cell biology is growing rapidly and is generating large amounts of data from a variety of species, disease conditions, tissues, and organs. Coordinated efforts such as CZI CELLxGENE, HuBMAP, Broad Institute Single Cell Portal, and DISCO, allow researchers to access large volumes of curated datasets. Although the majority of the data is from scRNAseq experiments, a wide range of other modalities are represented as well. These resources have created an opportunity to build and expand the computational biology ecosystem to develop tools necessary for data reuse, and for extracting novel biological insights. Here, we highlight achievements made so far, areas where further development is needed, and specific challenges that need to be overcome.

The HectoMAP spectroscopic survey provides a unique mass-limited sample of more than 35,000 quiescent galaxies ($D_n4000>1.5$) covering the redshift range $0.210^{10}\,M_\odot$) quiescent population at intermediate redshift. These high-quality summed spectra enable full spectrum fitting and the related extraction of the average stellar population age and metallicity. The average galaxy age increases with the central D$_n4000$ as expected. The correlation is essentially invariant with stellar mass; thus $D_n4000$ is a robust proxy for quiescent galaxy stellar population age. HectoMAP provides the first quiescent sample at intermediate redshift comparable with $z\sim0$ mass-complete datasets. Scaling relations derived from the HectoMAP summed spectra connect stellar age and metallicity with quiescent galaxy stellar mass up to $z\sim0.5$. Anti-correlation between the equivalent width of the [O II] emission line and stellar age, together with the mild increase in stellar age with stellar mass, supports a broad range of timescales for the mass assembly of intermediate-redshift quiescent systems. On average, the most massive galaxies ($M_\ast>10^{11}\, M_\odot$) assemble the bulk of their stars at earlier epochs. A strong increase in the average stellar metallicity with stellar mass, along with the correlation between the [O II] equivalent width and metallicity at $0.2

We present new multi-frequency ALMA continuum observations of the massive [$\log_{10}(M_\star/M_\odot) = 10.3_{-0.2}^{+0.1}$], UV-luminous [$M_\mathrm{UV} = -21.7 \pm 0.2$] $z=7.31$ galaxy REBELS-25 in Bands 3, 4, 5, and 9. Combining the new observations with previously-taken data in Bands 6 and 8, we cover the dust continuum emission of the galaxy in six distinct bands -- spanning rest-frame $50-350\,\mu$m -- enabling simultaneous constraints on its dust mass ($M_\mathrm{dust}$), temperature ($T_\mathrm{dust}$) and emissivity index ($\beta_\mathrm{IR}$) via modified blackbody fitting. Given a fiducial model of optically thin emission, we infer a cold dust temperature of $T_\mathrm{dust} = 32_{-6}^{+9}\,$K and a high dust mass of $\log_{10}(M_\mathrm{dust}/M_\odot) = 8.2_{-0.4}^{+0.6}$, and moderately optically thick dust does not significantly alter these estimates. If we assume dust production is solely through supernovae (SNe), the inferred dust yield would be high, $y = 0.7_{-0.4}^{+2.3}\,M_\odot$ per SN. Consequently, we argue grain growth in the interstellar medium of REBELS-25 also contributes to its dust build-up. This is supported by the steep dust emissivity index $\beta_\mathrm{IR} = 2.5 \pm 0.4$ we measure for REBELS-25, as well as by its high stellar mass, dense interstellar medium, and metal-rich nature. Our results suggest that constraining the dust emissivity indices of high-redshift galaxies is important not only to mitigate systematic uncertainties in their dust masses and obscured star formation rates, but also to assess if dust properties evolve across cosmic time. We present an efficient observing setup to do so with ALMA, combining observations of the peak and Rayleigh-Jeans tail of the dust emission., Comment: 14 pages main text, 6 figures + appendices; re-submitted to MNRAS after a positive referee report

Reinforcement Learning (RL) is used extensively in Autonomous Systems (AS) as it enables learning at runtime without the need for a model of the environment or predefined actions. However, most applications of RL in AS, such as those based on Q-learning, can only optimize one objective, making it necessary in multi-objective systems to combine multiple objectives in a single objective function with predefined weights. A number of Multi-Objective Reinforcement Learning (MORL) techniques exist but they have mostly been applied in RL benchmarks rather than real-world AS systems. In this work, we use a MORL technique called Deep W-Learning (DWN) and apply it to the Emergent Web Servers exemplar, a self-adaptive server, to find the optimal configuration for runtime performance optimization. We compare DWN to two single-objective optimization implementations: {\epsilon}-greedy algorithm and Deep Q-Networks. Our initial evaluation shows that DWN optimizes multiple objectives simultaneously with similar results than DQN and {\epsilon}-greedy approaches, having a better performance for some metrics, and avoids issues associated with combining multiple objectives into a single utility function., Comment: pages, Accepted to AI4AS 2024 workshop

Software vulnerabilities pose significant security challenges and potential risks to society, necessitating extensive efforts in automated vulnerability detection. There are two popular lines of work to address automated vulnerability detection. On one hand, Static Application Security Testing (SAST) is usually utilized to scan source code for security vulnerabilities, especially in industries. On the other hand, deep learning (DL)-based methods, especially since the introduction of large language models (LLMs), have demonstrated their potential in software vulnerability detection. However, there is no comparative study between SAST tools and LLMs, aiming to determine their effectiveness in vulnerability detection, understand the pros and cons of both SAST and LLMs, and explore the potential combination of these two families of approaches. In this paper, we compared 15 diverse SAST tools with 12 popular or state-of-the-art open-source LLMs in detecting software vulnerabilities from repositories of three popular programming languages: Java, C, and Python. The experimental results showed that SAST tools obtain low vulnerability detection rates with relatively low false positives, while LLMs can detect up 90\% to 100\% of vulnerabilities but suffer from high false positives. By further ensembling the SAST tools and LLMs, the drawbacks of both SAST tools and LLMs can be mitigated to some extent. Our analysis sheds light on both the current progress and future directions for software vulnerability detection.

Hierarchical federated learning (HFL) designs introduce intermediate aggregator nodes between clients and the global federated learning server in order to reduce communication costs and distribute server load. One side effect is that machine learning model replication at scale comes "for free" as part of the HFL process: model replicas are hosted at the client end, intermediate nodes, and the global server level and are readily available for serving inference requests. This creates opportunities for efficient model serving but simultaneously couples the training and serving processes and calls for their joint orchestration. This is particularly important for continual learning, where serving a model while (re)training it periodically, upon specific triggers, or continuously, takes place over shared infrastructure spanning the computing continuum. Consequently, training and inference workloads can interfere with detrimental effects on performance. To address this issue, we propose an inference load-aware HFL orchestration scheme, which makes informed decisions on HFL configuration, considering knowledge about inference workloads and the respective processing capacity. Applying our scheme to a continual learning use case in the transportation domain, we demonstrate that by optimizing aggregator node placement and device-aggregator association, significant inference latency savings can be achieved while communication costs are drastically reduced compared to flat centralized federated learning.

PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly knowledgeable base model that is effective to transfer. It achieves strong performance on a wide variety of open-world tasks. We evaluate PaliGemma on almost 40 diverse tasks including standard VLM benchmarks, but also more specialized tasks such as remote-sensing and segmentation., Comment: v2 adds Appendix H and I and a few citations

Current inferences of the BAO scale from galaxy clustering employ a reconstruction technique at fixed cosmology and bias parameters. Here, we present the first consistent joint Bayesian inference of the isotropic BAO scale, jointly varying the initial conditions as well as all bias coefficients, based on the EFT-based field-level forward model $\texttt{LEFTfield}$. We apply this analysis to mock data generated with a much higher cutoff (resolution), resulting in a significant model mismatch between mock data and the model used in the inference. We demonstrate that the remaining systematic bias in the BAO scale is below 2% for all data considered and below 1% when Eulerian bias is used for inference. Furthermore, we find that the inferred error on the BAO scale is up to 1.6 times smaller compared to that from a replication of the standard power-spectrum reconstruction approach, using the same scales as in the field-level inference, with the improvement growing towards smaller scales (higher $k$). Thus, a field-level approach to BAO not only allows for a consistent inference of the BAO scale, but promises to achieve more precise measurements on the same data as well., Comment: 25 pages, 15 figures

Text-to-image generative models are capable of producing high-quality images that often faithfully depict concepts described using natural language. In this work, we comprehensively evaluate a range of text-to-image models on numerical reasoning tasks of varying difficulty, and show that even the most advanced models have only rudimentary numerical skills. Specifically, their ability to correctly generate an exact number of objects in an image is limited to small numbers, it is highly dependent on the context the number term appears in, and it deteriorates quickly with each successive number. We also demonstrate that models have poor understanding of linguistic quantifiers (such as "a few" or "as many as"), the concept of zero, and struggle with more advanced concepts such as partial quantities and fractional representations. We bundle prompts, generated images and human annotations into GeckoNum, a novel benchmark for evaluation of numerical reasoning.

In this work we characterize the sets $E\subset X$ for which there is some $\alpha>0$ such that the function $d(\cdot,E)^{-\alpha}$ belongs to the Muckenhoupt class $A_1(X,d,\mu)$, where $(X,d,\mu)$ is a space of homogeneous type, extending a recent result obtained by Carlos Mudarra in metric spaces endowed with doubling measures. In particular, generalizations of the notions of weakly porous sets and doubling of the maximal hole function are given and it is shown that these concepts have a natural connection with the $A_1$ condition of some negative power of its distance function. The proof presented here is based on Whitney-type covering lemmas built on balls of a particular quasi-distance equivalent to the initial quasi-distance $d$ and provided by Roberto Mac\'ias and Carlos Segovia in "A well-behaved quasi-distance for spaces of homogeneous type", Trabajos de Matem\'atica 32, Instituto Argentino de Matem\'atica, 1981, 1-18., Comment: 21 pages

The star formation rate (SFR) is tightly connected to the amount of dense gas in molecular clouds. However, it is not fully understood how the relationship between dense molecular gas and star formation varies within galaxies and in different morphological environments. In this work, we study dense gas and star formation in the nearby spiral galaxy NGC 4321 to test how the amount of dense gas and its ability to form stars varies with environmental properties at 260 pc scales. We present new ALMA observations of HCN(1-0) line emission. Combined with existing CO(2-1) observations from ALMA, and H-alpha from MUSE, as well as F2100W from JWST to trace the SFR, we measure the HCN/CO line ratio, a proxy for the dense gas fraction and SFR/HCN, a proxy for the star formation efficiency of the dense gas. Towards the centre of the galaxy, HCN/CO systematically increases while SFR/HCN decreases, but these ratios stay roughly constant throughout the disc. Spiral arms, interarm regions, and bar ends show similar HCN/CO and SFR/HCN. On the bar, there is a significantly lower SFR/HCN at a similar HCN/CO. We conclude that the centres of galaxies show the strongest environmental influence on dense gas and star formation, suggesting either that clouds couple strongly to the surrounding pressure or that HCN is tracing more of the bulk molecular gas that is less efficiently converted into stars. On the contrary, across the disc of NGC 4321, where the ISM pressure is typically low, SFR/HCN does not show large variations (< 0.3 dex) in agreement with Galactic observations of molecular clouds. Despite the large variations across environments and physical conditions, HCN/CO is a good predictor of the mean molecular gas surface density at 260 pc scales., Comment: 18 pages, 9 figures, accepted for pub in A&A, Jun 13, 2024

Bilevel optimization, a well-established field for modeling hierarchical decision-making problems, has recently intersected with sustainability studies and practices, resulting in a series of works focusing on bilevel optimization problems involving multiple decision makers with diverse economic, environmental, and social objectives. This survey offers a comprehensive overview of sustainable bilevel optimization applications. First, we introduce the main concepts related to the nature of bilevel optimization problems and present some typical mathematical formulations for bilevel pricing problems that cover the majority of the collected applications. Then, we review the most relevant works published in sustainable bilevel optimization, giving a classification based on the application domains and their association with well-known operations research problems, while briefly discussing the proposed solution methodologies. We survey applications on transportation and logistics, production planning and manufacturing, water, waste, and agriculture management, supply chains, and disaster prevention and response. Finally, we outline a list of open questions and opportunities for future research in this domain.

We address a new prize-collecting problem of routing commodities in a given network with hub and non-hub nodes, in which the service of the non-hub nodes will be outsourced to third-party carriers. The problem is modeled as a Stackelberg game: there is a major firm (leader) that decides to serve a subset of commodities. The leader aims to outsource first and third legs of transportation services to smaller carriers (who act as followers) by allocating at most one carrier to each non-hub node. The carriers try to maximize their own profits, which are influenced by the leader's offers. The goal of the leader is to determine the optimal outsourcing fees, along with the allocation of carriers to the non-hub nodes, so that the profit from the routed commodities is maximized. The optimal response of the followers must be taken into account, as the followers might refuse to serve some legs in case they are negative or do not maximize their profit. We also study two alternative settings: one in which the outsourcing fees are fixed, and the other one in which the carriers accept any offer, as long as the resulting profit is non-negative. We prove that the set of possible outsourcing fees can be discretized and formulate the problem as a single-level mixed-integer nonlinear program. For all considered problem variants, we prove NP-hardness and propose and computationally investigate several MIP formulations. We study the computational scalability of these MIP formulations and analyze solutions obtained by varying the reservation prices of the carriers. Finally, by comparing the introduced problem variants, we derive some interesting managerial insights.

We address the long-standing problem of how to learn effective pixel-based image diffusion models at scale, introducing a remarkably simple greedy growing method for stable training of large-scale, high-resolution models. without the needs for cascaded super-resolution components. The key insight stems from careful pre-training of core components, namely, those responsible for text-to-image alignment {\it vs.} high-resolution rendering. We first demonstrate the benefits of scaling a {\it Shallow UNet}, with no down(up)-sampling enc(dec)oder. Scaling its deep core layers is shown to improve alignment, object structure, and composition. Building on this core model, we propose a greedy algorithm that grows the architecture into high-resolution end-to-end models, while preserving the integrity of the pre-trained representation, stabilizing training, and reducing the need for large high-resolution datasets. This enables a single stage model capable of generating high-resolution images without the need of a super-resolution cascade. Our key results rely on public datasets and show that we are able to train non-cascaded models up to 8B parameters with no further regularization schemes. Vermeer, our full pipeline model trained with internal datasets to produce 1024x1024 images, without cascades, is preferred by 44.0% vs. 21.4% human evaluators over SDXL.

4Hb-TaS$_2$ is a superconductor that exhibits unique characteristics such as time-reversal symmetry breaking, hidden magnetic memory, and topological edge modes. It is a naturally occurring heterostructure comprising of alternating layers of 1H-TaS$_2$ and 1T-TaS$_2$. The former is a well-known superconductor, while the latter is a correlated insulator with a possible non-trivial magnetic ground state. In this study, we use angle resolved photoemission spectroscopy to investigate the normal state electronic structure of this unconventional superconductor. Our findings reveal that the band structure of 4H-TaS$_2$ fundamentally differs from that of its constituent materials. Specifically, we observe a significant charge transfer from the 1T layers to the 1H layers that drives the 1T layers away from half-filling. In addition, we find a substantial reduction in inter-layer coupling in 4Hb-TaS$_2$ compared to the coupling in 2H-TaS$_2$ that results in a pronounced spin-valley locking within 4Hb-TaS$_2$