Search

As states reckon with racial enrollment and attainment gaps in higher education, some have made efforts to address them through their higher education funding. Two common approaches are outcomes-based funding (OBF) and Promise programs, as each can be designed with an explicit race equity lens. This report summarizes a two-year study examining the degree to which these race-specific state funding policies have advanced racial equity in higher education. Exploring initiatives in Minnesota, New Jersey, and North Carolina, this study examines how these policies aim to dismantle racial inequities by directing resources toward Black, Latinx, and Indigenous students and the institutions that serve them. This study draws on 25 interviews with state policymakers and institutional leaders at a purposive sample of public four-year institutions. Researchers sought the perspectives of individuals at Minority-serving Institutions (MSIs), Historically Black Colleges and Universities (HBCUs), Native American-serving non-tribal institutions (NASNTIs), and Hispanic-serving Institutions (HSIs), but also selected one Predominantly White Institution (PWI) in OBF states to understand how, if at all, the funding model incentivized institutional change. The research suggests that while policymakers express concerns that the amount of funding tied to race equity metrics is insufficient to motivate change, institutional leaders perceive that the metrics have steered funds toward under-resourced students and the institutions serving them. However, the report highlights that without addressing historical underfunding of MSIs and HBCUs, these institutions cannot compete equitably for funds under zero-sum OBF models. The report also suggests that the design of the formula, unfunded mandates, and competing state initiatives can undermine the impact of a race-explicit OBF. Race-explicit Promise programs in this study were perceived to have bolstered enrollment and retention at participating MSIs. However, because programs were designed to cover only tuition and fees, respondents suggested that they were not providing an additional benefit beyond existing federal and state aid programs. Without covering the additional costs of college, including room and board, these programs fell short of making a four-year residential college experience accessible to students for whom they were designed. The recommendations emerging from the research urge policymakers to consider the full ecosystem of postsecondary institutions when designing funding initiatives, ensuring that funding programs are additive rather than overlapping to maximize outcomes. The report also emphasizes the importance of supporting additional costs of college in Promise programs to promote equity for students experiencing systemic barriers.

This study introduces Bhirkuti's Test of Bias Acceptance, a systematic graphical framework for evaluating bias and determining its acceptability under varying experimental conditions. Absolute Relative Bias (ARB), while useful for understanding bias, is sensitive to outliers and population parameter magnitudes, often overstating bias for small values and understating it for larger ones. Similarly, Relative Efficiency (RE) can be influenced by variance differences and outliers, occasionally producing counterintuitive values exceeding 100%, which complicates interpretation. By addressing the limitations of traditional metrics such as Absolute Relative Bias (ARB) and Relative Efficiency (RE), the proposed graphical methodology framework leverages ridgeline plots and standardized estimate to provide a comprehensive visualization of parameter estimate distributions. Ridgeline plots done this way offer a robust alternative by visualizing full distributions, highlighting variability, trends, outliers, descriptive and facilitating more informed decision-making. This study employs multivariate Latent Growth Models (LGM) and Monte Carlo simulations to examine the performance of growth curve modeling under planned missing data designs, focusing on parameter estimate recovery and efficiency. By combining innovative visualization techniques with rigorous simulation methods, Bhirkuti's Test of Bias Acceptance provides a versatile and interpretable toolset for advancing quantitative research in bias evaluation and efficiency assessment.

The deterministic generation of robust soliton comb has significant meaning for the optical frequency combs to be widely used in various applications. As a novel form of microcomb, Soliton crystal holds the advantages of easy generation, high conversion efficiency, and excellent thermal robustness. Here, we report the turnkey deterministic generation of "Palm-like" soliton crystal with a free-running scheme. The robustness of the turnkey soliton crystal generation is also investigated in multiple aspects, including the success rate, the thermal robustness, and the long-term stability. The experiment results reveal our turnkey soliton crystal can achieve nearly a 100% success rate with a power variation less than 1.5 dB over one hundred trials of two samples, is insensitive to thermal effect, and is robust to the environment during four-hour laboratory time., Comment: 10 pages, 5 figures

In this study, we conduct a parameter error analysis for the 3D modified Leray-$\alpha$ model using both analytical and numerical approaches. We first prove the global well-posedness and continuous dependence of initial data for the assimilated system. Furthermore, given sufficient conditions on the physical parameters and norms of the true solution, we demonstrate that the true solution can be recovered from the approximation solution, with an error determined by the discrepancy between the true and approximating parameters. Numerical simulations are provided to validate the convergence criteria., Comment: 27 pages, 12 figures. arXiv admin note: text overlap with arXiv:2409.03042

In this work we establish under certain hypotheses the $N \to +\infty$ asymptotic expansion of integrals of the form $$\mathcal{Z}_{N,\Gamma}[V] \, = \, \int_{\Gamma^N} \prod_{ a < b}^{N}(z_a - z_b)^\beta \, \prod_{k=1}^{N} \mathrm{e}^{ - N \beta V(z_k) } \, \mathrm{d}\mathbf{z}$$ where $V \in \mathbb{C}[X]$, $\beta \in 2 \mathbb{N}^*$ is an even integer and $\Gamma \subset \mathbb{C}$ is an unbounded contour such that the integral converges. For even degree, real valued $V$s and when $\Gamma = \mathbb{R}$, it is well known that the large-$N$ expansion is characterised by an equilibrium measure corresponding to the minimiser of an appropriate energy functional. This method bears a structural resemblance with the Laplace method. By contrast, in the complex valued setting we are considering, the analysis structurally resembles the classical steepest-descent method, and involves finding a critical point \textit{and} a steepest descent curve, the latter being a deformation of the original integration contour. More precisely, one minimises a curve-dependent energy functional with respect to measures on the curve and then maximises the energy over an appropriate space of curves. Our analysis deals with the one-cut regime of the associated equilibrium measure. We establish the existence of an all order asymptotic expansion for $\ln \mathcal{Z}_{N,\Gamma}[V]$ and explicitly identify the first few terms., Comment: 64 pages

To date there is little publicly available scientific data on Unidentified Aerial Phenomena (UAP) whose properties and kinematics purportedly reside outside the performance envelope of known phenomena. To address this deficiency, the Galileo Project is designing, building, and commissioning a multi-modal ground-based observatory to continuously monitor the sky and conduct a rigorous long-term aerial census of all aerial phenomena, including natural and human-made. One of the key instruments is an all-sky infrared camera array using eight uncooled long-wave infrared FLIR Boson 640 cameras. Their calibration includes a novel extrinsic calibration method using airplane positions from Automatic Dependent Surveillance-Broadcast (ADS-B) data. We establish a first baseline for the system performance over five months of field operation, using a real-world dataset derived from ADS-B data, synthetic 3-D trajectories, and a hand-labelled real-world dataset. We report acceptance rates (e.g. viewable airplanes that are recorded) and detection efficiencies (e.g. recorded airplanes which are successfully detected) for a variety of weather conditions, range and aircraft size. We reconstruct $\sim$500,000 trajectories of aerial objects from this commissioning period. A toy outlier search focused on large sinuosity of the 2-D reconstructed trajectories flags about 16% of trajectories as outliers. After manual review, 144 trajectories remain ambiguous: they are likely mundane objects but cannot be elucidated at this stage of development without distance and kinematics estimation or other sensor modalities. Our observed count of ambiguous outliers combined with systematic uncertainties yields an upper limit of 18,271 outliers count for the five-month interval at a 95% confidence level. This likelihood-based method to evaluate significance is applicable to all of our future outlier searches.

A major limitation of machine learning (ML) prediction models is that they recover associational, rather than causal, predictive relationships between variables. In high-stakes automation applications of ML this is problematic, as the model often learns spurious, non-causal associations. This paper proposes mechanism learning, a simple method which uses front-door causal bootstrapping to deconfound observational data such that any appropriate ML model is forced to learn predictive relationships between effects and their causes (reverse causal inference), despite the potential presence of multiple unknown and unmeasured confounding. Effect variables can be very high dimensional, and the predictive relationship nonlinear, as is common in ML applications. This novel method is widely applicable, the only requirement is the existence of a mechanism variable mediating the cause (prediction target) and effect (feature data), which is independent of the (unmeasured) confounding variables. We test our method on fully synthetic, semi-synthetic and real-world datasets, demonstrating that it can discover reliable, unbiased, causal ML predictors where by contrast, the same ML predictor trained naively using classical supervised learning on the original observational data, is heavily biased by spurious associations. We provide code to implement the results in the paper, online., Comment: 12 pages, 6 figures

Text-To-Image (TTI) Diffusion Models such as DALL-E and Stable Diffusion are capable of generating images from text prompts. However, they have been shown to perpetuate gender stereotypes. These models process data internally in multiple stages and employ several constituent models, often trained separately. In this paper, we propose two novel metrics to measure bias internally in these multistage multimodal models. Diffusion Bias was developed to detect and measures bias introduced by the diffusion stage of the models. Bias Amplification measures amplification of bias during the text-to-image conversion process. Our experiments reveal that TTI models amplify gender bias, the diffusion process itself contributes to bias and that Stable Diffusion v2 is more prone to gender bias than DALL-E 2.

Recent advances in supercontinuum light generation have been remarkable, particularly in the context of highly nonlinear photonic integrated waveguides. In this study, we thoroughly investigate supercontinuum (SC) generation in high-index doped silica glass integrated waveguides, exploring various femtosecond pumping wavelengths and input polarization states. We demonstrate broadband SC generation spanning from 700 nm to 2400 nm when pumping within the anomalous dispersion regime at 1200 nm, 1300 nm, and 1550 nm. In contrast, pumping within the normal dispersion regime at 1000 nm results in narrower SC spectra, primarily due to coherent nonlinear effects such as self-phase modulation and optical wave breaking. Additionally, we examine the impact of TE/TM polarization modes on SC generation, shedding light on the polarization-dependent characteristics of the broadening process. Moreover, Raman scattering measurements reveal the emergence of two new peaks at 48.8 THz and 75.1 THz in the Raman gain curve. Our experimental results are supported by numerical simulations based on a generalized nonlinear Schrodinger equation that incorporates the new Raman gain contribution. Finally, relative intensity noise measurements conducted using the dispersive Fourier transform technique indicate excellent stability of the generated SC spectra., Comment: 21 pages, 13 figures

With the advent of Large Language Models (LLMs) and Multimodal (Visio-lingual) LLMs, a flurry of research has emerged, analyzing the performance of such models across a diverse array of tasks. While most studies focus on evaluating the capabilities of state-of-the-art (SoTA) MLLM models through task accuracy (e.g., Visual Question Answering, grounding) across various datasets, our work explores the related but complementary aspect of consistency - the ability of an MLLM model to produce semantically similar or identical responses to semantically similar queries. We note that consistency is a fundamental prerequisite (necessary but not sufficient condition) for robustness and trust in MLLMs. Humans, in particular, are known to be highly consistent (even if not always accurate) in their responses, and consistency is inherently expected from AI systems. Armed with this perspective, we propose the MM-R$^3$ benchmark, which analyses the performance in terms of consistency and accuracy in SoTA MLLMs with three tasks: Question Rephrasing, Image Restyling, and Context Reasoning. Our analysis reveals that consistency does not always align with accuracy, indicating that models with higher accuracy are not necessarily more consistent, and vice versa. Furthermore, we propose a simple yet effective mitigation strategy in the form of an adapter module trained to minimize inconsistency across prompts. With our proposed strategy, we are able to achieve absolute improvements of 5.7% and 12.5%, on average on widely used MLLMs such as BLIP-2 and LLaVa 1.5M in terms of consistency over their existing counterparts.

In this study, we conduct parameter estimation analysis on a data assimilation algorithm for two turbulence models: the simplified Bardina model and the Navier-Stokes-{\alpha} model. Our approach involves creating an approximate solution for the turbulence models by employing an interpolant operator based on the observational data of the systems. The estimation depends on the parameter alpha in the models. Additionally, numerical simulations are presented to validate our theoretical results, Comment: 24 pictures

We present the first measurement of the missing energy due to nuclear effects in monoenergetic, muon neutrino charged-current interactions on carbon, originating from $K^+ \rightarrow \mu^+ \nu_\mu$ decay-at-rest ($E_{\nu_\mu}=235.5$ MeV), performed with the JSNS$^2$ liquid scintillator based experiment. Towards characterizing the neutrino interaction, ostensibly $\nu_\mu n \rightarrow \mu^- p$ or $\nu_\mu$$^{12}\mathrm{C}$ $\rightarrow \mu^-$$^{12}\mathrm{N}$, and in analogy to similar electron scattering based measurements, we define the missing energy as the energy transferred to the nucleus ($\omega$) minus the kinetic energy of the outgoing proton(s), $E_{m} \equiv \omega-\sum T_p$, and relate this to visible energy in the detector, $E_{m}=E_{\nu_\mu}~(235.5~\mathrm{MeV})-m_\mu~(105.7~\mathrm{MeV}) - E_{vis}$. The missing energy, which is naively expected to be zero in the absence of nuclear effects (e.g. nucleon separation energy, Fermi momenta, and final-state interactions), is uniquely sensitive to many aspects of the interaction, and has previously been inaccessible with neutrinos. The shape-only, differential cross section measurement reported, based on a $(77\pm3)$% pure double-coincidence KDAR signal (621 total events), provides an important benchmark for models and event generators at 100s-of-MeV neutrino energies, characterized by the difficult-to-model transition region between neutrino-nucleus and neutrino-nucleon scattering, and relevant for applications in nuclear physics, neutrino oscillation measurements, and Type-II supernova studies.

Event Cameras, also known as Neuromorphic sensors, capture changes in local light intensity at the pixel level, producing asynchronously generated data termed ``events''. This distinct data format mitigates common issues observed in conventional cameras, like under-sampling when capturing fast-moving objects, thereby preserving critical information that might otherwise be lost. However, leveraging this data often necessitates the development of specialized, handcrafted event representations that can integrate seamlessly with conventional Convolutional Neural Networks (CNNs), considering the unique attributes of event data. In this study, We evaluate event-based Face and Eye tracking. The core objective of our study is to showcase the viability of integrating conventional algorithms with event-based data, transformed into a frame format while preserving the unique benefits of event cameras. To validate our approach, we constructed a frame-based event dataset by simulating events between RGB frames derived from the publicly accessible Helen Dataset. We assess its utility for face and eye detection tasks through the application of GR-YOLO -- a pioneering technique derived from YOLOv3. This evaluation includes a comparative analysis with results derived from training the dataset with YOLOv8. Subsequently, the trained models were tested on real event streams from various iterations of Prophesee's event cameras and further evaluated on the Faces in Event Stream (FES) benchmark dataset. The models trained on our dataset shows a good prediction performance across all the datasets obtained for validation with the best results of a mean Average precision score of 0.91. Additionally, The models trained demonstrated robust performance on real event camera data under varying light conditions., Comment: This paper has been accepted at The Workshop On Neuromorphic Vision: Advantages and Applications of Event Cameras at the European Conference on Computer Vision (ECCV), 2024

Status epilepticus (SE) carries risks of morbidity and mortality. Experimental studies have implicated the entorhinal cortex in prolonged seizures; however, studies in large human cohorts are limited. We hypothesised that individuals with temporal lobe epilepsy (TLE) and a history of SE would have more severe entorhinal atrophy compared to others with TLE and no history of SE. 357 individuals with drug resistant temporal lobe epilepsy (TLE) and 100 healthy controls were scanned on a 3T MRI. For all subjects the cortex was segmented, parcellated, and the thickness calculated from the T1-weighted anatomical scan. Subcortical volumes were derived similarly. Cohen's d and Wilcoxon rank-sum tests respectively were used to capture effect sizes and significance. Individuals with TLE and SE had reduced entorhinal thickness compared to those with TLE and no history of SE. The entorhinal cortex was more atrophic ipsilaterally (d=0.51, p<0.001) than contralaterally (d=0.37, p=0.01). Reductions in ipsilateral entorhinal thickness were present in both left TLE (n=22:176, d=0.78, p<0.001), and right TLE (n=19:140, d=0.31, p=0.04), albeit with a smaller effect size in right TLE. Several other regions exhibited atrophy in individuals with TLE, but these did not relate to a history of SE. These findings suggest potential involvement or susceptibility of the entorhinal cortex in prolonged seizures.

Saccades are extremely rapid movements of both eyes that occur simultaneously, typically observed when an individual shifts their focus from one object to another. These movements are among the swiftest produced by humans and possess the potential to achieve velocities greater than that of blinks. The peak angular speed of the eye during a saccade can reach as high as 700{\deg}/s in humans, especially during larger saccades that cover a visual angle of 25{\deg}. Previous research has demonstrated encouraging outcomes in comprehending neurological conditions through the study of saccades. A necessary step in saccade detection involves accurately identifying the precise location of the pupil within the eye, from which additional information such as gaze angles can be inferred. Conventional frame-based cameras often struggle with the high temporal precision necessary for tracking very fast movements, resulting in motion blur and latency issues. Event cameras, on the other hand, offer a promising alternative by recording changes in the visual scene asynchronously and providing high temporal resolution and low latency. By bridging the gap between traditional computer vision and event-based vision, we present events as frames that can be readily utilized by standard deep learning algorithms. This approach harnesses YOLOv8, a state-of-the-art object detection technology, to process these frames for pupil tracking using the publicly accessible Ev-Eye dataset. Experimental results demonstrate the framework's effectiveness, highlighting its potential applications in neuroscience, ophthalmology, and human-computer interaction., Comment: This paper is a preprint of a paper submitted to the 26th Irish Machine Vision and Image Processing Conference (IMVIP 2024). If accepted, the copy of record will be available at IET Digital Library

Molecular HIV Surveillance (MHS) has been described as key to enabling rapid responses to HIV outbreaks. It operates by linking individuals with genetically similar viral sequences, which forms a network. A major limitation of MHS is that it depends on sequence collection, which very rarely covers the entire population of interest. Ignoring missing data by conducting complete case analysis--which assumes that the observed network is complete--has been shown to result in significantly biased estimates of network properties. We use MHS to investigate disease dynamics of the HIV epidemic in Miami-Dade County (MDC) among men who have sex with men (MSM)--only 30.1% have a reported sequence. To do so, we present an approach for making Bayesian inferences on partially observed networks. Through a simulation study, we demonstrate a reduction in error of 43%-63% between our estimates and complete case analyses. We estimate increased mixing between MSM communities in MDC, defined by race and transmission risk compared to the results based on complete case analysis. Our approach makes use of a flexible network model--congruence class model--to overcome the high computational burden of previously reported Bayesian approaches to estimate network properties from partially observed networks., Comment: 19 pages; 6 figures; 2 tables

The American Enterprise Institute, EducationCounsel, and The Century Foundation undertook a joint process to examine--across ideological lines--the nature of the existing system that finances graduate education, including its benefits and downsides, and to design a framework that should guide the improvement of federal policy regarding graduate student financing. This report aims to outline policy options that address the burden on students, particularly the disproportionate burden facing students of color, and the growing cost of the graduate loan programs for taxpayers. The shared goal of this process was improved outcomes for students and better value for taxpayers. Analysis and discussion of different policy options led to the conclusion that any politically viable and effective approach must address five different dimensions of the problem through the following set of policy levers: (1) set reasonable loan limits; (2) award grant aid to students and institutions to address equity and social good considerations; (3) ensure sufficient value and return on investment for students and taxpayers; (4) enhance the regulatory structure and consumer protections for private lending; and (5) improve data disclosure and transparency.

We demonstrate a CMOS-foundry-fabricated piezo-optomechanical photonic integrated circuit platform for ultraviolet and blue wavelengths, using alumina waveguides that are strongly mechanically coupled to monolithically integrated aluminum nitride piezoelectric actuators. Low waveguide losses are measured down to at least 320 nm, where we achieve 1.6 dB/cm. This allows us to demonstrate broadband amplitude modulators based on piezoelectrically actuated MEMS cantilever phase-shifters down to 320 nm, with a high extinction ratio of 30 dB. We further demonstrate the versatility of the platform by designing and demonstrating a modulator that can work with high extinction and low loss at 320 nm and 420 nm, simultaneously, demonstrating control of multiple, disparate wavelengths in one device. We also demonstrate narrow-band resonant racetrack modulators with quality factors of 4.7E5 and a tuning rate of 27.5 MHz/V. These results should open doors for a range of novel applications in UV photonics, quantum science, sensing and spectroscopy.

The aim of this paper is to give a new explicit construction of Lusztig's asymptotic algebra in affine type $\mathsf{A}$. To do so, we construct a balanced system of cell modules, prove an asymptotic version of the Plancherel Theorem and develop a relative version of the Satake Isomorphism for each two-sided Kazhdan-Lusztig cell.

Magnetic resonance imaging (MRI) is a crucial tool to identify brain abnormalities in a wide range of neurological disorders. In focal epilepsy MRI is used to identify structural cerebral abnormalities. For covert lesions, machine learning and artificial intelligence algorithms may improve lesion detection if abnormalities are not evident on visual inspection. The success of this approach depends on the volume and quality of training data. Herein, we release an open-source dataset of preprocessed MRI scans from 442 individuals with drug-refractory focal epilepsy who had neurosurgical resections, and detailed demographic information. The MRI scan data includes the preoperative 3D T1 and where available 3D FLAIR, as well as a manually inspected complete surface reconstruction and volumetric parcellations. Demographic information includes age, sex, age of onset of epilepsy, location of surgery, histopathology of resected specimen, occurrence and frequency of focal seizures with and without impairment of awareness, focal to bilateral tonic-clonic seizures, number of anti-seizure medications (ASMs) at time of surgery, and a total of 1764 patient years of post-surgical follow up. Crucially, we also include resection masks delineated from post-surgical imaging. To demonstrate the veracity of our data, we successfully replicated previous studies showing long-term outcomes of seizure freedom in the range of around 50%. Our imaging data replicates findings of group level atrophy in patients compared to controls. Resection locations in the cohort were predominantly in the temporal and frontal lobes. We envisage our dataset, shared openly with the community, will catalyse the development and application of computational methods in clinical neurology.

Normative models of brain structure estimate the effects of covariates such as age and sex using large samples of healthy controls. These models can then be applied to e.g. smaller clinical cohorts to distinguish disease effects from other covariates. However, these advanced statistical modelling approaches can be difficult to access, and processing large healthy cohorts is computationally demanding. Thus, accessible platforms with pre-trained normative models are needed. We present such a platform for brain morphology analysis as an open-source web application (https://cnnplab.shinyapps.io/BrainMoNoCle/), with six key features: (i) user-friendly web interface, (ii) individual and group outputs, (iii) multi-site analysis, (iv) regional and whole-brain analysis, (v) integration with existing tools, and (vi) featuring multiple morphology metrics. Using a diverse sample of 3,276 healthy controls across 21 sites, we pre-trained normative models on various metrics. We validated the models with a small sample of individuals with bipolar disorder, showing outputs that aligned closely with existing literature only after applying our normative modelling. Using a cohort of people with temporal lobe epilepsy, we showed that individual-level abnormalities were in line with seizure lateralisation. Finally, with the ability to investigate multiple morphology measures in the same framework, we found that biological covariates are better explained in specific morphology measures, and for applications, only some measures are sensitive to the disease process. Our platform offers a comprehensive framework to analyse brain morphology in clinical and research settings. Validations confirm the superiority of normative models and the advantage of investigating a range of brain morphology metrics together.

We present a novel experimental concept to search for proton decay. Using paleo-detectors, ancient minerals acquired from deep underground which can hold traces of charged particles, it may be possible to conduct a search for $p \to \bar{\nu} K^+$ via the track produced at the endpoint of the kaon. Such a search is not possible on Earth due to large atmospheric-neutrino-induced backgrounds. However, the Moon offers a reprieve from this background, since the conventional component of the cosmic-ray-induced neutrino flux at the Moon is significantly suppressed due to the Moon's lack of atmosphere. For a 100 g, $10^9$ year old (100 kton$\cdot$year exposure) sample of olivine extracted from the Moon, we expect about 0.5 kaon endpoints due to neutrino backgrounds, including secondary interactions. If such a lunar paleo-detector sample can be acquired and efficiently analyzed, proton decay sensitivity exceeding $\tau_p\sim10^{34}$ years may be achieved, competitive with Super-Kamiokande's current published limit ($\tau_p>5.9\times 10^{33}$ years at 90% CL) and the projected reach of DUNE and Hyper-Kamiokande in the $p \to \bar{\nu} K^+$ channel. This concept is clearly futuristic, not least since it relies on extracting mineral samples from a few kilometers below the surface of the Moon and then efficiently scanning them for kaon endpoint induced crystal defects with sub-micron-scale resolution. However, the search for proton decay is in urgent need of a paradigm shift, and paleo-detectors could provide a promising alternative to conventional experiments., Comment: 12 pages, 4 figures

Large language models (LLMs) trained on general domain corpora showed remarkable results on natural language processing (NLP) tasks. However, previous research demonstrated LLMs trained using domain-focused corpora perform better on specialized tasks. Inspired by this insight, we developed INDUS, a comprehensive suite of LLMs tailored for the closely-related domains of Earth science, biology, physics, heliophysics, planetary sciences and astrophysics, and trained using curated scientific corpora drawn from diverse data sources. The suite of models include: (1) an encoder model trained using domain-specific vocabulary and corpora to address NLP tasks, (2) a contrastive-learning based text embedding model trained using a diverse set of datasets to address information retrieval tasks and (3) smaller versions of these models created using knowledge distillation for applications which have latency or resource constraints. We also created three new scientific benchmark datasets, CLIMATE-CHANGE NER (entity-recognition), NASA-QA (extractive QA) and NASA-IR (IR) to accelerate research in these multi-disciplinary fields. We show that our models outperform both general-purpose (RoBERTa) and domain-specific (SCIBERT) encoders on these new tasks as well as existing tasks in the domains of interest. Furthermore, we demonstrate the use of these models in two industrial settings -- as a retrieval model for large-scale vector search applications and in automatic content tagging systems., Comment: EMNLP 2024 (Industry Track)

The $K$-medoids problem is a challenging combinatorial clustering task, widely used in data analysis applications. While numerous algorithms have been proposed to solve this problem, none of these are able to obtain an exact (globally optimal) solution for the problem in polynomial time. In this paper, we present EKM: a novel algorithm for solving this problem exactly with worst-case $O\left(N^{K+1}\right)$ time complexity. EKM is developed according to recent advances in transformational programming and combinatorial generation, using formal program derivation steps. The derived algorithm is provably correct by construction. We demonstrate the effectiveness of our algorithm by comparing it against various approximate methods on numerous real-world datasets. We show that the wall-clock run time of our algorithm matches the worst-case time complexity analysis on synthetic datasets, clearly outperforming the exponential time complexity of benchmark branch-and-bound based MIP solvers. To our knowledge, this is the first, rigorously-proven polynomial time, practical algorithm for this ubiquitous problem.

Leakage out of the computational subspace is a major limitation of current state-of-the-art neutral-atom quantum computers and a significant challenge for scalable systems. In a quantum processor with cesium atoms, we demonstrate proof-of-principle circuit-based conversion of leakage errors to erasure errors via Leakage Detection Units (LDUs), which non-destructively map information about the presence or absence of the qubit onto the state of an ancilla. With a standard LDU circuit, we successfully convert leakage errors to erasure errors for all major leakage pathways while preserving the quantum information in the case that no leakage occurred. We benchmark the performance of the LDU using a three-outcome low-loss state detection method and also explore the advantages of three-outcome measurements for LDUs. We find that the LDU detects atom-loss errors with ~93.4% accuracy, limited by technical imperfections of our apparatus. We further compile and execute a SWAP LDU, wherein the roles of the original data atom and ancilla atom are exchanged under the action of the LDU, providing 'free refilling' of atoms in the case of leakage errors. This circuit-based leakage-to-erasure error conversion is a critical component of a neutral-atom quantum processor where the quantum information may significantly outlive the lifetime of any individual atom in the quantum register.

Wearable sensors such as smartwatches have become ubiquitous in recent years, allowing the easy and continual measurement of physiological parameters such as heart rate, physical activity, body temperature, and blood glucose in an every-day setting. This multi-modal data offers the potential to identify latent states occurring across physiological measures, which may represent important bio-behavioural states that could not be observed in any single measure. Here we present an approach, utilising a hidden semi-Markov model, to identify such states in data collected using a smartwatch, electrocardiogram, and blood glucose monitor, over two weeks from a sample of 9 participants. We found 26 latent ultradian states across the sample, with many occurring at particular times of day. Here we describe some of these, as well as their association with subjective mood and time use diaries. These methods provide a novel avenue for developing insights into the physiology of everyday life.

In this note, we show how certain everywhere-regular real rational function solutions of the KP1 equation ("multi-lumps") can be constructed via the polynomial analogs of theta functions from singular rational curves with cusps. We use two methods, one direct and the other producing a degeneration of the well-understood soliton solutions from nodal singular curves. The second approach can be seen as a variation on the long-wave limit technique of Ablowitz and Satsuma, as developed by Zhang, Yang, Li, Guo, and Stepanyants. We present an explicit example of a three-lump solution constructed via the polynomial analog of the theta function from a rational curve with two cuspidal singular points, each with semigroup $\langle 2,5\rangle$. (In the theory of curve singularities, these are known as $A_4$ double points.) We conjecture that these ideas will generalize to give similar $M$-lump solutions with $M = \frac{N(N+1)}{2}$ for $N > 2$ starting from rational curves with two singular points with semigroup $\langle 2,2N+1\rangle$ ($A_{2N}$ double points). We also show a five-lump solution obtained from a curve with two cusps with semigroup $\langle 3,4\rangle$. Similar solutions have been constructed by other methods previously; our contribution is to show how they arise from the algebraic-geometric setting by considering singular curves with several cusps, as in previous work of Agostini, Celik, and Little., Comment: 15 pages, 5 figures. Revised and reorganized version giving more details on background from the article by Agostini, Celik, and Little; a second construction method; and an additional example

The emergence of attention-based transformer models has led to their extensive use in various tasks, due to their superior generalization and transfer properties. Recent research has demonstrated that such models, when prompted appropriately, are excellent for few-shot inference. However, such techniques are under-explored for dense prediction tasks like semantic segmentation. In this work, we examine the effectiveness of prompting a transformer-decoder with learned visual prompts for the generalized few-shot segmentation (GFSS) task. Our goal is to achieve strong performance not only on novel categories with limited examples, but also to retain performance on base categories. We propose an approach to learn visual prompts with limited examples. These learned visual prompts are used to prompt a multiscale transformer decoder to facilitate accurate dense predictions. Additionally, we introduce a unidirectional causal attention mechanism between the novel prompts, learned with limited examples, and the base prompts, learned with abundant data. This mechanism enriches the novel prompts without deteriorating the base class performance. Overall, this form of prompting helps us achieve state-of-the-art performance for GFSS on two different benchmark datasets: COCO-$20^i$ and Pascal-$5^i$, without the need for test-time optimization (or transduction). Furthermore, test-time optimization leveraging unlabelled test data can be used to improve the prompts, which we refer to as transductive prompt tuning., Comment: Accepted at CVPR 2024

Synthetic data has a key role to play in data sharing by statistical agencies and other generators of statistical data products. Generative Adversarial Networks (GANs), typically applied to image synthesis, are also a promising method for tabular data synthesis. However, there are unique challenges in tabular data compared to images, eg tabular data may contain both continuous and discrete variables and conditional sampling, and, critically, the data should possess high utility and low disclosure risk (the risk of re-identifying a population unit or learning something new about them), providing an opportunity for multi-objective (MO) optimization. Inspired by MO GANs for images, this paper proposes a smart MO evolutionary conditional tabular GAN (SMOE-CTGAN). This approach models conditional synthetic data by applying conditional vectors in training, and uses concepts from MO optimisation to balance disclosure risk against utility. Our results indicate that SMOE-CTGAN is able to discover synthetic datasets with different risk and utility levels for multiple national census datasets. We also find a sweet spot in the early stage of training where a competitive utility and extremely low risk are achieved, by using an Improvement Score. The full code can be downloaded from https://github.com/HuskyNian/SMO\_EGAN\_pytorch.

The Segment Anything Model (SAM) and CLIP are remarkable vision foundation models (VFMs). SAM, a prompt driven segmentation model, excels in segmentation tasks across diverse domains, while CLIP is renowned for its zero shot recognition capabilities. However, their unified potential has not yet been explored in medical image segmentation. To adapt SAM to medical imaging, existing methods primarily rely on tuning strategies that require extensive data or prior prompts tailored to the specific task, making it particularly challenging when only a limited number of data samples are available. This work presents an in depth exploration of integrating SAM and CLIP into a unified framework for medical image segmentation. Specifically, we propose a simple unified framework, SaLIP, for organ segmentation. Initially, SAM is used for part based segmentation within the image, followed by CLIP to retrieve the mask corresponding to the region of interest (ROI) from the pool of SAM generated masks. Finally, SAM is prompted by the retrieved ROI to segment a specific organ. Thus, SaLIP is training and fine tuning free and does not rely on domain expertise or labeled data for prompt engineering. Our method shows substantial enhancements in zero shot segmentation, showcasing notable improvements in DICE scores across diverse segmentation tasks like brain (63.46%), lung (50.11%), and fetal head (30.82%), when compared to un prompted SAM. Code and text prompts are available at: https://github.com/aleemsidra/SaLIP.

JSNS$^2$ searches for short baseline neutrino oscillations with a baseline of 24~meters and a target of 17~tonnes of the Gd-loaded liquid scintillator. The correct algorithm on the event reconstruction of events, which determines the position and energy of neutrino interactions in the detector, are essential for the physics analysis of the data from the experiment. Therefore, the performance of the event reconstruction is carefully checked with calibrations using $^{252}$Cf source. This manuscript describes the methodology and the performance of the event reconstruction.

Ensemble methods, particularly boosting, have established themselves as highly effective and widely embraced machine learning techniques for tabular data. In this paper, we aim to leverage the robust predictive power of traditional boosting methods while enhancing fairness and interpretability. To achieve this, we develop Fair MP-Boost, a stochastic boosting scheme that balances fairness and accuracy by adaptively learning features and observations during training. Specifically, Fair MP-Boost sequentially samples small subsets of observations and features, termed minipatches (MP), according to adaptively learned feature and observation sampling probabilities. We devise these probabilities by combining loss functions, or by combining feature importance scores to address accuracy and fairness simultaneously. Hence, Fair MP-Boost prioritizes important and fair features along with challenging instances, to select the most relevant minipatches for learning. The learned probability distributions also yield intrinsic interpretations of feature importance and important observations in Fair MP-Boost. Through empirical evaluation of simulated and benchmark datasets, we showcase the interpretability, accuracy, and fairness of Fair MP-Boost.