Search

PSR J1618-3921 is one of five known millisecond pulsars (MSPs) in eccentric orbits (eMPSs) located in the Galactic plane, whose formation is poorly understood. Earlier studies of these objects revealed significant discrepancies between observation and predictions from standard binary evolution scenarios of pulsar-Helium white dwarf binaries. We conducted observations with the L-band receiver of the MeerKAT radio telescope and the UWL receiver of the Parkes Murriyang radio telescope between 2019 and 2021. These data were added to archival observations. We perform an analysis of this joint 23-year-dataset. We use the recent observations to give a brief account of the emission properties of J1618-3921, including a Rotating Vector model fit of the linear polarisation position angle of the pulsar. The long timing baseline allowed for a highly significant measurement of the rate of advance of periastron of $\dot{\omega}$. We can only report a low significance detection of the orthometric Shapiro delay parameters $h_3$ and $\varsigma$, leading to mass estimates of the total and individual binary masses. We detect an unexpected change in the orbital period of, which is an order of magnitude larger and carries an opposite sign to what is expected from Galactic acceleration and the Shklovskii effect. We also detect a significant second derivative of the spin frequency. Furthermore, we report an unexpected, abrupt change of the mean pulse profile in June 2021 with unknown origin. We propose that the anomalous $\dot{P_b}$ and $\ddot{f}$ indicate an additional varying acceleration due to a nearby mass, i.e., the J1618-3921 binary system is likely part of a hierarchical triple. This finding suggests that at least some eMSPs might have formed in triple star systems. Although the uncertainties are large, the binary companion mass is consistent with the $P_b$ - $M_{WD}$ relation., Comment: 17 pages, 11 figures, 3 tables

Feature-mapping methods for topology optimization (FMTO) facilitate direct geometry extraction by leveraging high-level geometric descriptions of the designs. However, FMTO often relies solely on Boolean unions, which can restrict the design space. This work proposes an FMTO framework leveraging an expanded set of Boolean operations, namely, union, intersection, and subtraction. The optimization process entails determining the primitives and the optimal Boolean operation tree. In particular, the framework leverages a recently proposed unified Boolean operation approach. This approach presents a continuous and differentiable function that interpolates the Boolean operations, enabling gradient-based optimization. The proposed methodology is agnostic to the specific primitive parametrization and is showcased through various numerical examples., Comment: Submitted to Structural and Multidisciplinary Optimization

We introduce picasso, a model designed to predict thermodynamic properties of the intracluster medium based on the properties of halos in gravity-only simulations. The predictions result from the combination of an analytical gas model, mapping gas properties to the gravitational potential, and of a machine learning model to predict the model parameters for individual halos based on their scalar properties, such as mass and concentration. Once trained, the model can be applied to make predictions for arbitrary potential distributions, allowing its use with flexible inputs such as N-body particle distributions or radial profiles. We present the model, and train it using pairs of gravity-only and hydrodynamic simulations. We show that when trained on non-radiative hydrodynamic simulations, picasso can make remarkably accurate and precise predictions of intracluster gas thermodynamics. Training the model on full-physics simulations yields robust predictions as well, albeit with slightly degraded performance. We further show that the model can be trained to make accurate predictions from very minimal information, at the cost of modestly reduced precision. picasso is made publicly available as a Python package, which includes trained models that can be used to make predictions easily and efficiently, in a fully auto-differentiable and hardware-accelerated framework., Comment: 17 pages, 11 figures, 3 tables; for submission to the Open Journal of Astrophysics

In top-down enumeration for program synthesis, abstraction-based pruning uses an abstract domain to approximate the set of possible values that a partial program, when completed, can output on a given input. If the set does not contain the desired output, the partial program and all its possible completions can be pruned. In its general form, abstraction-based pruning requires manually designed, domain-specific abstract domains and semantics, and thus has only been used in domain-specific synthesizers. This paper provides sufficient conditions under which a form of abstraction-based pruning can be automated for arbitrary synthesis problems in the general-purpose Semantics-Guided Synthesis (SemGuS) framework without requiring manually-defined abstract domains. We show that if the semantics of the language for which we are synthesizing programs exhibits some monotonicity properties, one can obtain an abstract interval-based semantics for free from the concrete semantics of the programming language, and use such semantics to effectively prune the search space. We also identify a condition that ensures such abstract semantics can be used to compute a precise abstraction of the set of values that a program derivable from a given hole in a partial program can produce. These precise abstractions make abstraction-based pruning more effective. We implement our approach in a tool, Moito, which can tackle synthesis problems defined in the SemGuS framework. Moito can automate interval-based pruning without any a-priori knowledge of the problem domain, and solve synthesis problems that previously required domain-specific, abstraction-based synthesizers -- e.g., synthesis of regular expressions, CSV file schema, and imperative programs from examples.

Background: Data quality is vital in software analytics, particularly for machine learning (ML) applications like software defect prediction (SDP). Despite the widespread use of ML in software engineering, the effect of data quality antipatterns on these models remains underexplored. Objective: This study develops a taxonomy of ML-specific data quality antipatterns and assesses their impact on software analytics models' performance and interpretation. Methods: We identified eight types and 14 sub-types of ML-specific data quality antipatterns through a literature review. We conducted experiments to determine the prevalence of these antipatterns in SDP data (RQ1), assess how cleaning order affects model performance (RQ2), evaluate the impact of antipattern removal on performance (RQ3), and examine the consistency of interpretation from models built with different antipatterns (RQ4). Results: In our SDP case study, we identified nine antipatterns. Over 90% of these overlapped at both row and column levels, complicating cleaning prioritization and risking excessive data removal. The order of cleaning significantly impacts ML model performance, with neural networks being more resilient to cleaning order changes than simpler models like logistic regression. Antipatterns such as Tailed Distributions and Class Overlap show a statistically significant correlation with performance metrics when other antipatterns are cleaned. Models built with different antipatterns showed moderate consistency in interpretation results. Conclusion: The cleaning order of different antipatterns impacts ML model performance. Five antipatterns have a statistically significant correlation with model performance when others are cleaned. Additionally, model interpretation is moderately affected by different data quality antipatterns.

The Kondo problem, which describes the interaction of a spin $s$ magnetic impurity with a free Fermi gas, is a classic example of strongly coupled physics. Historically, the problem has been solved by Wilson's numerical renormalization group and later by Bethe ansatz. In this paper, we present an alternate analytic solution of the Kondo problem that combines an expansion in $1/s$ with the renormalization group. We study both the case of an impurity interacting with a single channel $K=1$ of fermions in the $s \rightarrow \infty$ limit and the case with $K$ channels in the double-scaling limit $K \rightarrow \infty$, $s \to \infty$, $K/s$ fixed. Our approach allows us to describe analytically intermediate scales of the Kondo problem at large $s$ and compute thermodynamic observables such as the impurity entropy and susceptibility. We find these observables to agree with the Bethe ansatz results. We also compute the impurity spectral function, finite temperature resistivity and the Kondo screening cloud profile, properties that are not easily accessible from Bethe ansatz. Notably, in the regime $K > 2s$ we access the "non-Fermi-liquid" overscreened fixed point of the multichannel Kondo problem.

We explore a versatile technique for inverse designing 2D photonic crystal metasurfaces. These surfaces, known for their ability to manipulate light-matter interactions, can be precisely controlled to achieve specific functionalities. The key lies in efficiently optimizing the geometric patterns and dimensions of the metasurface. Through a composite method which exploits two well-established paradigms - Covariance Matrix Adaptation optimization and Rigorous Coupled Wave Analysis (RCWA), we demonstrate our ability to design and optimize resonances in metaelements to achieve desired optical performance such as near-perfect absorption at chosen wavelengths/optical modes, which otherwise proves to be challenging or even impossible with conventional inverse design implementations. We apply our method to design three-layered structures involving a monolayer absorber, transparent metasubstrate, and a back mirror to get near 100% absorption at one or two chosen wavelengths. For illustration, we choose black phosphorus and silicon metasurface to predict ~100% absorption in a monolayer at 1550 nm. The versatile technique can be applied to tailor reflectance and transmittance for any optical mode and wavelength. This computationally efficient design method paves the way for creating high-performance 2D metasurface-based devices with a variety of applications, including quantum technology components such as single photon sensors and biphoton sources, communication systems, and non-linear light conversion.

The Koopman autoencoder, a data-driven technique, has gained traction for modeling nonlinear dynamics using deep learning methods in recent years. Given the linear characteristics inherent to the Koopman operator, controlling its eigenvalues offers an opportunity to enhance long-term prediction performance, a critical task for forecasting future trends in time-series datasets with long-term behaviors. However, controlling eigenvalues is challenging due to high computational complexity and difficulties in managing them during the training process. To tackle this issue, we propose leveraging the singular value decomposition (SVD) of the Koopman matrix to adjust the singular values for better long-term prediction. Experimental results demonstrate that, during training, the loss term for singular values effectively brings the eigenvalues close to the unit circle, and the proposed approach outperforms existing baseline methods for long-term prediction tasks., Comment: 6 pages, 5 figures, to be presented at IEEE MLSP 2024

Research organisms provide invaluable insights into human biology and diseases, serving as essential tools for functional experiments, disease modeling, and drug testing. However, evolutionary divergence between humans and research organisms hinders effective knowledge transfer across species. Here, we review state-of-the-art methods for computationally transferring knowledge across species, primarily focusing on methods that utilize transcriptome data and/or molecular networks. We introduce the term "agnology" to describe the functional equivalence of molecular components regardless of evolutionary origin, as this concept is becoming pervasive in integrative data-driven models where the role of evolutionary origin can become unclear. Our review addresses four key areas of information and knowledge transfer across species: (1) transferring disease and gene annotation knowledge, (2) identifying agnologous molecular components, (3) inferring equivalent perturbed genes or gene sets, and (4) identifying agnologous cell types. We conclude with an outlook on future directions and several key challenges that remain in cross-species knowledge transfer.

The momentum ray transform $I_m^k$ integrates a rank $m$ symmetric tensor field $f$ on ${\mathbb R}^n$ over lines with the weight $t^k$, $I_m^kf(x,\xi)=\int_{-\infty}^\infty t^k\langle f(x+t\xi),\xi^m\rangle\,\mathrm{d}t$. Let $N^k_m=(I^k_m)^*I^k_m$ be the normal operator of $I_m^k$. To what extent is a symmetric $m$-tensor field $f$ determined by the data $(N_m^0f,\dots,N_m^rf)$ given for some $0\le r\le m$? The Saint Venant operator $W^r_m$ is a linear differential operator of order $m-r$ with constant coefficients on the space of symmetric $m$-tensor fields. We derive an explicit formula expressing $W^r_mf$ in terms of $(N_m^0f,\dots,N_m^rf)$. The tensor field $W^r_mf$ represents the full local information on $f$ that can be extracted from the data $(N_m^0f,\dots,N_m^rf)$., Comment: 10 pages. arXiv admin note: text overlap with arXiv:2401.00791

Current methods for performing 3D reconstruction and novel view synthesis (NVS) in ultrasound imaging data often face severe artifacts when training NeRF-based approaches. The artifacts produced by current approaches differ from NeRF floaters in general scenes because of the unique nature of ultrasound capture. Furthermore, existing models fail to produce reasonable 3D reconstructions when ultrasound data is captured or obtained casually in uncontrolled environments, which is common in clinical settings. Consequently, existing reconstruction and NVS methods struggle to handle ultrasound motion, fail to capture intricate details, and cannot model transparent and reflective surfaces. In this work, we introduced NeRF-US, which incorporates 3D-geometry guidance for border probability and scattering density into NeRF training, while also utilizing ultrasound-specific rendering over traditional volume rendering. These 3D priors are learned through a diffusion model. Through experiments conducted on our new "Ultrasound in the Wild" dataset, we observed accurate, clinically plausible, artifact-free reconstructions.

Liver allograft failure occurs in approximately 20% of liver transplant recipients within five years post-transplant, leading to mortality or the need for retransplantation. Providing an accurate and interpretable model for individualized risk estimation of graft failure is essential for improving post-transplant care. To this end, we introduce the Model for Allograft Survival (MAS), a simple linear risk score that outperforms other advanced survival models. Using longitudinal patient follow-up data from the United States (U.S.), we develop our models on 82,959 liver transplant recipients and conduct multi-site evaluations on 11 regions. Additionally, by testing on a separate non-U.S. cohort, we explore the out-of-distribution generalization performance of various models without additional fine-tuning, a crucial property for clinical deployment. We find that the most complex models are also the ones most vulnerable to distribution shifts despite achieving the best in-distribution performance. Our findings not only provide a strong risk score for predicting long-term graft failure but also suggest that the routine machine learning pipeline with only in-distribution held-out validation could create harmful consequences for patients at deployment., Comment: Accepted at MLHC 2024

The Large Magellanic Cloud (LMC) presents a unique environment for pulsar population studies due to its distinct star formation characteristics and proximity to the Milky Way. As part of the TRAPUM (TRAnsients and PUlsars with MeerKAT) Large Survey Project, we are using the core array of the MeerKAT radio telescope (MeerKAT) to conduct a targeted search of the LMC for radio pulsars at L-band frequencies, 856-1712$\,$MHz. The excellent sensitivity of MeerKAT, coupled with a 2-hour integration time, makes the survey 3 times more sensitive than previous LMC radio pulsar surveys. We report the results from the initial four survey pointings which has resulted in the discovery of seven new radio pulsars, increasing the LMC radio pulsar population by 30 per cent. The pulse periods of these new pulsars range from 278 to 1690$\,$ms, and the highest dispersion measure is 254.20$\,$pc$\,$cm$^{-3}$. We searched for, but did not find any significant pulsed radio emission in a beam centred on the SN$\,$1987A remnant, establishing an upper limit of 6.3$\,{\mu}$Jy on its minimum flux density at 1400$\,$MHz., Comment: 12 pages, 4 figures, 4 tables. Accepted for publication in Monthly Notices of the Royal Astronomical Society

We compute the second moment of the Riemann zeta function for shifted arguments over a domain that extends the ones in the literature. We use the Riemann-Siegel formula for the error term in the approximate functional equation and take the products of all the terms into account. We also show that, as a function of imaginary shifts on the critical line, the the second moment behaves like a Fourier-Cauchy type kernel on a class of functions. This is reminiscent of orthogonal functions., Comment: 17 pages

We report new radio timing solutions from a three-year observing campaign conducted with the MeerKAT and Murriyang telescopes for nine Small Magellanic Cloud pulsars, increasing the number of characterised rotation-powered extragalactic pulsars by 40 per cent. We can infer from our determined parameters that the pulsars are seemingly all isolated, that six are ordinary pulsars, and that three of the recent MeerKAT discoveries have a young characteristic age of under 100 kyr and have undergone a spin-up glitch. Two of the sources, PSRs J0040$-$7337 and J0048$-$7317, are energetic young pulsars with spin-down luminosities of the order of 10$^{36}$ erg s$^{-1}$. They both experienced a large glitch, with a change in frequency of about 30 $\mu$Hz, and a frequency derivative change of order $-10^{-14}$ Hz s$^{-1}$. These glitches, the inferred glitch rate, and the properties of these pulsars (including potentially high inter-glitch braking indices) suggest these neutron stars might be Vela-like repeating glitchers and should be closely monitored in the future. The position and energetics of PSR J0048$-$7317 confirm it is powering a new Pulsar Wind Nebula (PWN) detected as a radio continuum source; and similarly the association of PSR J0040$-$7337 with the PWN of Supernova Remnant (SNR) DEM S5 (for which we present a new Chandra image) is strengthened. Finally, PSR J0040$-$7335 is also contained within the same SNR but is a chance superposition. It has also been seen to glitch with a change of frequency of $10^{-2}$ $\mu$Hz. This work more than doubles the characterised population of SMC radio pulsars., Comment: 20 pages, 13 figures, accepted for publication in Monthly Notices of the Royal Astronomical Society

To date, there has been no comprehensive study characterizing the effect of diffusion-weighted magnetic resonance imaging voxel resolution on the resulting connectome for high resolution subject data. Similarity in results improved with higher resolution, even after initial down-sampling. To ensure robust tractography and connectomes, resample data to 1 mm isotropic resolution.

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language models (LLMs) for workflow anomaly detection by exploiting their ability to learn complex data patterns. Two approaches are investigated: 1) supervised fine-tuning (SFT), where pre-trained LLMs are fine-tuned on labeled data for sentence classification to identify anomalies, and 2) in-context learning (ICL) where prompts containing task descriptions and examples guide LLMs in few-shot anomaly detection without fine-tuning. The paper evaluates the performance, efficiency, generalization of SFT models, and explores zero-shot and few-shot ICL prompts and interpretability enhancement via chain-of-thought prompting. Experiments across multiple workflow datasets demonstrate the promising potential of LLMs for effective anomaly detection in complex executions., Comment: 12 pages, 14 figures, paper is accepted by SC'24, source code, see: https://github.com/PoSeiDon-Workflows/LLM_AD

Semantic segmentation has emerged as a pivotal area of study in computer vision, offering profound implications for scene understanding and elevating human-machine interactions across various domains. While 2D semantic segmentation has witnessed significant strides in the form of lightweight, high-precision models, transitioning to 3D semantic segmentation poses distinct challenges. Our research focuses on achieving efficiency and lightweight design for 3D semantic segmentation models, similar to those achieved for 2D models. Such a design impacts applications of 3D semantic segmentation where memory and latency are of concern. This paper introduces a novel approach to 3D semantic segmentation, distinguished by incorporating a hybrid blend of 2D and 3D computer vision techniques, enabling a streamlined, efficient process. We conduct 2D semantic segmentation on RGB images linked to 3D point clouds and extend the results to 3D using an extrusion technique for specific class labels, reducing the point cloud subspace. We perform rigorous evaluations with the DeepViewAgg model on the complete point cloud as our baseline by measuring the Intersection over Union (IoU) accuracy, inference time latency, and memory consumption. This model serves as the current state-of-the-art 3D semantic segmentation model on the KITTI-360 dataset. We can achieve heightened accuracy outcomes, surpassing the baseline for 6 out of the 15 classes while maintaining a marginal 1% deviation below the baseline for the remaining class labels. Our segmentation approach demonstrates a 1.347x speedup and about a 43% reduced memory usage compared to the baseline., Comment: 18 pages, 3 figures, 3 tables

We introduce FedDM, a novel training framework designed for the federated training of diffusion models. Our theoretical analysis establishes the convergence of diffusion models when trained in a federated setting, presenting the specific conditions under which this convergence is guaranteed. We propose a suite of training algorithms that leverage the U-Net architecture as the backbone for our diffusion models. These include a basic Federated Averaging variant, FedDM-vanilla, FedDM-prox to handle data heterogeneity among clients, and FedDM-quant, which incorporates a quantization module to reduce the model update size, thereby enhancing communication efficiency across the federated network. We evaluate our algorithms on FashionMNIST (28x28 resolution), CIFAR-10 (32x32 resolution), and CelebA (64x64 resolution) for DDPMs, as well as LSUN Church Outdoors (256x256 resolution) for LDMs, focusing exclusively on the imaging modality. Our evaluation results demonstrate that FedDM algorithms maintain high generation quality across image resolutions. At the same time, the use of quantized updates and proximal terms in the local training objective significantly enhances communication efficiency (up to 4x) and model convergence, particularly in non-IID data settings, at the cost of increased FID scores (up to 1.75x)., Comment: 13 pages,3 figures, 2 algorithms, 3 tables

PSR J1227$-$6208 is a 34.53-ms recycled pulsar with a massive companion. This system has long been suspected to belong to the emerging class of massive recycled pulsar-ONeMg white dwarf systems such as PSR J2222$-$0137, PSR J1528$-$3146 and J1439$-$5501. Here we present an updated emission and timing analysis with more than 11 years of combined Parkes and MeerKAT data, including 19 hours of high-frequency data from the newly installed MeerKAT S-band receivers. We measure a scattering timescale of 1.22 ms at 1 GHz with a flat scattering index 3.33<$\beta$<3.62, and a mean flux density of 0.53-0.62 mJy at 1 GHz with a steep spectral index 2.06<$\alpha$<2.35. Around 15% of the emission is linearly and circularly polarised, but the polarisation angle does not follow the rotating vector model. Thanks to the sensitivity of MeerKAT, we successfully measure a rate of periastron advance of 0.0171(11) deg/yr, and a Shapiro delay with an orthometric amplitude of 3.6$\pm$0.5 $\mu$s and an orthometric shape of 0.85$\pm$0.05. The main source of uncertainty in our timing analysis is chromatic correlated dispersion measure noise, which we model as a power law in the Fourier space thanks to the large frequency coverage provided by the Parkes UWL receiver. Assuming general relativity and accounting for the measurements across all the implemented timing noise models, the total mass, companion mass, pulsar mass and inclination angle are constrained at 2.3

It has been suggested that black hole microstates in string theory may have "no interiors". The arguments of arXiv:2312.14108 suggest that even if this were the case, conventional bulk EFT should be valid at the horizon for black holes that are not too old. Here, we explore the validity of bulk EFT for young black holes from a different perspective, by considering the gravitational collapse of scalar moduli. This builds on arXiv:2003.05488, which studied the numerical collapse of a scalar field in a Choptuik-like set up. Evidence was presented there for two observations -- (a) For every scalar profile that results in collapse, the scalar field undergoes trans-Planckian variation, (b) Every trans-Planckian scalar motion is hidden behind an apparent horizon. The results of arXiv:2003.05488 were mostly obtained in regimes close to critical collapse, where scale-separation was difficult to achieve. In this paper, we study the same system in super-critical regimes. This allows us to study the localization properties of scalar variations inside the apparent horizon by separating the horizon and singularity scales. We find strong evidence that the $\mathcal{O}(1)$ scalar variation is localized around the curvature divergence, and is hierarchically well-separated from the apparent horizon. Because $\mathcal{O}(1)$ scalar movement is associated to the breakdown of bulk EFT according to the swampland distance conjecture, this is an indication that bulk EFT is well-behaved in the interiors of young black holes. Our results suggest the perspective that cosmic censorship is a mechanism for preserving bulk EFT between the horizon and the singularity., Comment: 16 pages, 16 plots

Artificial intelligence and machine learning frameworks have served as computationally efficient mapping between inputs and outputs for engineering problems. These mappings have enabled optimization and analysis routines that have warranted superior designs, ingenious material systems and optimized manufacturing processes. A common occurrence in such modeling endeavors is the existence of multiple source of data, each differentiated by fidelity, operating conditions, experimental conditions, and more. Data fusion frameworks have opened the possibility of combining such differentiated sources into single unified models, enabling improved accuracy and knowledge transfer. However, these frameworks encounter limitations when the different sources are heterogeneous in nature, i.e., not sharing the same input parameter space. These heterogeneous input scenarios can occur when the domains differentiated by complexity, scale, and fidelity require different parametrizations. Towards addressing this void, a heterogeneous multi-source data fusion framework is proposed based on input mapping calibration (IMC) and latent variable Gaussian process (LVGP). In the first stage, the IMC algorithm is utilized to transform the heterogeneous input parameter spaces into a unified reference parameter space. In the second stage, a multi-source data fusion model enabled by LVGP is leveraged to build a single source-aware surrogate model on the transformed reference space. The proposed framework is demonstrated and analyzed on three engineering case studies (design of cantilever beam, design of ellipsoidal void and modeling properties of Ti6Al4V alloy). The results indicate that the proposed framework provides improved predictive accuracy over a single source model and transformed but source unaware model., Comment: 20 Pages,9 Figures, Data is available per request

When Large Language Models (LLMs) are compressed using techniques such as quantization, the predominant way to demonstrate the validity of such techniques is by measuring the model's accuracy on various benchmarks.If the accuracies of the baseline model and the compressed model are close, it is assumed that there was negligible degradation in quality.However, even when the accuracy of baseline and compressed model are similar, we observe the phenomenon of flips, wherein answers change from correct to incorrect and vice versa in proportion.We conduct a detailed study of metrics across multiple compression techniques, models and datasets, demonstrating that the behavior of compressed models as visible to end-users is often significantly different from the baseline model, even when accuracy is similar.We further evaluate compressed models qualitatively and quantitatively using MT-Bench and show that compressed models are significantly worse than baseline models in this free-form generative task.Thus, we argue that compression techniques should also be evaluated using distance metrics.We propose two such metrics, KL-Divergence and flips, and show that they are well correlated.

We propose OmniNOCS, a large-scale monocular dataset with 3D Normalized Object Coordinate Space (NOCS) maps, object masks, and 3D bounding box annotations for indoor and outdoor scenes. OmniNOCS has 20 times more object classes and 200 times more instances than existing NOCS datasets (NOCS-Real275, Wild6D). We use OmniNOCS to train a novel, transformer-based monocular NOCS prediction model (NOCSformer) that can predict accurate NOCS, instance masks and poses from 2D object detections across diverse classes. It is the first NOCS model that can generalize to a broad range of classes when prompted with 2D boxes. We evaluate our model on the task of 3D oriented bounding box prediction, where it achieves comparable results to state-of-the-art 3D detection methods such as Cube R-CNN. Unlike other 3D detection methods, our model also provides detailed and accurate 3D object shape and segmentation. We propose a novel benchmark for the task of NOCS prediction based on OmniNOCS, which we hope will serve as a useful baseline for future work in this area. Our dataset and code will be at the project website: https://omninocs.github.io., Comment: Accepted to ECCV 2024, project website: https://omninocs.github.io

Enterprise chatbots, powered by generative AI, are emerging as key applications to enhance employee productivity. Retrieval Augmented Generation (RAG), Large Language Models (LLMs), and orchestration frameworks like Langchain and Llamaindex are crucial for building these chatbots. However, creating effective enterprise chatbots is challenging and requires meticulous RAG pipeline engineering. This includes fine-tuning embeddings and LLMs, extracting documents from vector databases, rephrasing queries, reranking results, designing prompts, honoring document access controls, providing concise responses, including references, safeguarding personal information, and building orchestration agents. We present a framework for building RAG-based chatbots based on our experience with three NVIDIA chatbots: for IT/HR benefits, financial earnings, and general content. Our contributions are three-fold: introducing the FACTS framework (Freshness, Architectures, Cost, Testing, Security), presenting fifteen RAG pipeline control points, and providing empirical results on accuracy-latency tradeoffs between large and small LLMs. To the best of our knowledge, this is the first paper of its kind that provides a holistic view of the factors as well as solutions for building secure enterprise-grade chatbots.", Comment: 8 pages, 6 figures, 2 tables, Preprint submission to ACM CIKM 2024

Knowing the effect of an intervention is critical for human decision-making, but current approaches for causal effect estimation rely on manual data collection and structuring, regardless of the causal assumptions. This increases both the cost and time-to-completion for studies. We show how large, diverse observational text data can be mined with large language models (LLMs) to produce inexpensive causal effect estimates under appropriate causal assumptions. We introduce NATURAL, a novel family of causal effect estimators built with LLMs that operate over datasets of unstructured text. Our estimators use LLM conditional distributions (over variables of interest, given the text data) to assist in the computation of classical estimators of causal effect. We overcome a number of technical challenges to realize this idea, such as automating data curation and using LLMs to impute missing information. We prepare six (two synthetic and four real) observational datasets, paired with corresponding ground truth in the form of randomized trials, which we used to systematically evaluate each step of our pipeline. NATURAL estimators demonstrate remarkable performance, yielding causal effect estimates that fall within 3 percentage points of their ground truth counterparts, including on real-world Phase 3/4 clinical trials. Our results suggest that unstructured text data is a rich source of causal effect information, and NATURAL is a first step towards an automated pipeline to tap this resource., Comment: 28 pages, 11 figures

A widespread adoption of Virtual, Augmented, and Mixed Reality (VR/AR/MR), collectively referred to as Extended Reality (XR), has become a tangible possibility to revolutionize educational and training scenarios by offering immersive, interactive experiences. In this paper we present \textsf{INTERACT}, an authoring tool for creating advanced 3D physics-based Intelligent Tutoring Systems (ITS) by individual developers or small-scale development teams. \textsf{INTERACT} is based on a cutting edge physics engine allowing realistic interactions such as collision detection and ergonomic evaluations. We demonstrate the benefits of \textsf{INTERACT} by developing a set of training scenarios for a use case of a Laser cutting machine. The use case illustrates the numerous possibilities such as creating interaction with objects, ease of configuring a scenario and how to design the visual effects to the machine.

Bindings for machine learning frameworks (such as TensorFlow and PyTorch) allow developers to integrate a framework's functionality using a programming language different from the framework's default language (usually Python). In this paper, we study the impact of using TensorFlow and PyTorch bindings in C#, Rust, Python and JavaScript on the software quality in terms of correctness (training and test accuracy) and time cost (training and inference time) when training and performing inference on five widely used deep learning models. Our experiments show that a model can be trained in one binding and used for inference in another binding for the same framework without losing accuracy. Our study is the first to show that using a non-default binding can help improve machine learning software quality from the time cost perspective compared to the default Python binding while still achieving the same level of correctness.

Automatically locating a bug within a large codebase remains a significant challenge for developers. Existing techniques often struggle with generalizability and deployment due to their reliance on application-specific data and large model sizes. This paper proposes a novel pre-trained language model (PLM) based technique for bug localization that transcends project and language boundaries. Our approach leverages contrastive learning to enhance the representation of bug reports and source code. It then utilizes a novel ranking approach that combines commit messages and code segments. Additionally, we introduce a knowledge distillation technique that reduces model size for practical deployment without compromising performance. This paper presents several key benefits. By incorporating code segment and commit message analysis alongside traditional file-level examination, our technique achieves better bug localization accuracy. Furthermore, our model excels at generalizability - trained on code from various projects and languages, it can effectively identify bugs in unseen codebases. To address computational limitations, we propose a CPU-compatible solution. In essence, proposed work presents a highly effective, generalizable, and efficient bug localization technique with the potential to real-world deployment.

We report on the results of an image-based search for pulsar candidates toward the Galactic bulge. We used mosaic images from the MeerKAT radio telescope, that were taken as part of a 173 deg**2 survey of the bulge and Galactic center of our Galaxy at L band (856-1712 MHz) in all four Stokes I, Q, U and V. The image root-mean-square noise levels of 12-17 uJy/ba represent a significant increase in sensitivity over past image-based pulsar searches. Our primary search criterion was circular polarization, but we used other criteria including linear polarization, in-band spectral index, compactness, variability and multi-wavelength counterparts to select pulsar candidates. We first demonstrate the efficacy of this technique by searching for polarized emission from known pulsars, and comparing our results with measurements from the literature. Our search resulted in a sample of 75 polarized pulsar candidates. Bright stars or young stellar objects were associated with 28 of these sources, including a small sample of highly polarized dwarf stars with pulsar-like steep spectra. Comparing the properties of this sample with the known pulsars, we identified 30 compelling candidates for pulsation follow-up, including two sources with both strong circular and linear polarization. The remaining 17 sources are either pulsars or stars, but we cannot rule out an extragalactic origin or image artifacts among the brighter, flat spectrum objects., Comment: 28 pages, 10 figures, 6 tables. ApJ, submitted