Search

Grain boundaries (GBs) govern critical properties of polycrystals. Although significant advancements have been made in characterizing minimum energy GBs, real GBs are seldom found in such states, making it challenging to establish structure-property relationships. This diversity of atomic arrangements in metastable states motivates using data-driven methods to establish these relationships. In this study, we utilize a vast atomistic database (~5000) of minimum energy and metastable states of symmetric tilt copper GBs, combined with physically-motivated local atomic environment (LAE) descriptors (Strain Functional Descriptors, SFDs) to predict GB properties. Our regression models exhibit robust predictive capabilities using only 19 descriptors, generalizing to atomic environments in nanocrystals. A significant highlight of our work is integration of an unsupervised method with SFDs to elucidate LAEs at GBs and their role in determining properties. Our research underscores the role of a physics-based representation of LAEs and efficacy of data-driven methods in establishing GB structure-property relationships.

The ability to shop independently, especially in grocery stores, is important for maintaining a high quality of life. This can be particularly challenging for people with visual impairments (PVI). Stores carry thousands of products, with approximately 30,000 new products introduced each year in the US market alone, presenting a challenge even for modern computer vision solutions. Through this work, we present a proof-of-concept socially assistive robotic system we call ShelfHelp, and propose novel technical solutions for enhancing instrumented canes traditionally meant for navigation tasks with additional capability within the domain of shopping. ShelfHelp includes a novel visual product locator algorithm designed for use in grocery stores and a novel planner that autonomously issues verbal manipulation guidance commands to guide the user during product retrieval. Through a human subjects study, we show the system's success in locating and providing effective manipulation guidance to retrieve desired products with novice users. We compare two autonomous verbal guidance modes achieving comparable performance to a human assistance baseline and present encouraging findings that validate our system's efficiency and effectiveness and through positive subjective metrics including competence, intelligence, and ease of use., Comment: 8 pages, 14 figures and charts

Growing interest and investment in the capabilities of foundation models has positioned such systems to impact a wide array of public services. Alongside these opportunities is the risk that these systems reify existing power imbalances and cause disproportionate harm to marginalized communities. Participatory approaches hold promise to instead lend agency and decision-making power to marginalized stakeholders. But existing approaches in participatory AI/ML are typically deeply grounded in context - how do we apply these approaches to foundation models, which are, by design, disconnected from context? Our paper interrogates this question. First, we examine existing attempts at incorporating participation into foundation models. We highlight the tension between participation and scale, demonstrating that it is intractable for impacted communities to meaningfully shape a foundation model that is intended to be universally applicable. In response, we develop a blueprint for participatory foundation models that identifies more local, application-oriented opportunities for meaningful participation. In addition to the "foundation" layer, our framework proposes the "subfloor'' layer, in which stakeholders develop shared technical infrastructure, norms and governance for a grounded domain, and the "surface'' layer, in which affected communities shape the use of a foundation model for a specific downstream task. The intermediate "subfloor'' layer scopes the range of potential harms to consider, and affords communities more concrete avenues for deliberation and intervention. At the same time, it avoids duplicative effort by scaling input across relevant use cases. Through three case studies in clinical care, financial services, and journalism, we illustrate how this multi-layer model can create more meaningful opportunities for participation than solely intervening at the foundation layer., Comment: 13 pages, 2 figures. Appeared at FAccT '24

The market for domestic robots made to perform household chores is growing as these robots relieve people of everyday responsibilities. Domestic robots are generally welcomed for their role in easing human labor, in contrast to industrial robots, which are frequently criticized for displacing human workers. But before these robots can carry out domestic chores, they need to become proficient in several minor activities, such as recognizing their surroundings, making decisions, and picking up on human behaviors. Reinforcement learning, or RL, has emerged as a key robotics technology that enables robots to interact with their environment and learn how to optimize their actions to maximize rewards. However, the goal of Deep Reinforcement Learning is to address more complicated, continuous action-state spaces in real-world settings by combining RL with Neural Networks. The efficacy of DeepRL can be further augmented through interactive feedback, in which a trainer offers real-time guidance to expedite the robot's learning process. Nevertheless, the current methods have drawbacks, namely the transient application of guidance that results in repeated learning under identical conditions. Therefore, we present a novel method to preserve and reuse information and advice via Deep Interactive Reinforcement Learning, which utilizes a persistent rule-based system. This method not only expedites the training process but also lessens the number of repetitions that instructors will have to carry out. This study has the potential to advance the development of household robots and improve their effectiveness and efficiency as learners.

Reinforcement Learning with Human Feedback (RLHF) is considered a standard approach to fine-tuning Large Language Models (LLMs). However, such methods often face limitations such as unsound black-box reward models, difficulties in collecting human preference data, and the reliance on sparse scalar rewards. These methods often fall short when applied to tasks that require complex domain-specific understanding. To address these challenges, we propose a new fine-tuning paradigm we refer to as Reinforcement Learning via Symbolic Feedback (RLSF), which aims to improve domain-specific understanding of LLMs more effectively than traditional reward signals. In the RLSF setting, the LLM being fine-tuned is considered an RL agent, while the environment is allowed access to reasoning or domain knowledge tools (e.g., solvers, provers, algebra systems, or knowledge bases). Crucially, in RLSF, these reasoning tools can provide feedback to the LLMs via poly-sized certificates (e.g., proofs), that characterize errors in the LLM-generated object with respect to some correctness specification. As a bonus, our RLSF approach does not require the reasoning systems we use to be differentiable. The ability of RLSF-based fine-tuning to leverage certificate-generating symbolic tools enables sound fine-grained (token-level) reward signals to LLMs, and thus addresses the limitations of traditional reward models mentioned above. Via extensive evaluations, we show that our RLSF-based fine-tuning of LLMs outperforms traditional approaches on five different applications, namely, program synthesis from natural language pseudo-code to programming language, three chemistry tasks, and solving the Game of 24. A takeaway is that fine-tuning via RLSF enables relatively smaller LLMs to significantly outperform closed-source models that are orders of magnitude larger (e.g., GPT-4).

Artificial Intelligence is poised to transform the design of complex, large-scale detectors like the ePIC at the future Electron Ion Collider. Featuring a central detector with additional detecting systems in the far forward and far backward regions, the ePIC experiment incorporates numerous design parameters and objectives, including performance, physics reach, and cost, constrained by mechanical and geometric limits. This project aims to develop a scalable, distributed AI-assisted detector design for the EIC (AID(2)E), employing state-of-the-art multiobjective optimization to tackle complex designs. Supported by the ePIC software stack and using Geant4 simulations, our approach benefits from transparent parameterization and advanced AI features. The workflow leverages the PanDA and iDDS systems, used in major experiments such as ATLAS at CERN LHC, the Rubin Observatory, and sPHENIX at RHIC, to manage the compute intensive demands of ePIC detector simulations. Tailored enhancements to the PanDA system focus on usability, scalability, automation, and monitoring. Ultimately, this project aims to establish a robust design capability, apply a distributed AI-assisted workflow to the ePIC detector, and extend its applications to the design of the second detector (Detector-2) in the EIC, as well as to calibration and alignment tasks. Additionally, we are developing advanced data science tools to efficiently navigate the complex, multidimensional trade-offs identified through this optimization process., Comment: 11 pages, 4 figures, AI4EIC 2023 proceeding

The CODEX-$\beta$ apparatus is a demonstrator for the proposed future CODEX-b experiment, a long-lived-particle detector foreseen for operation at IP8 during HL-LHC data-taking. The demonstrator project, intended to collect data in 2025, is described, with a particular focus on the design, construction, and installation of the new apparatus.

During the first half of the fourth observing run (O4a) of the International Gravitational Wave Network (IGWN), the Zwicky Transient Facility (ZTF) conducted a systematic search for kilonova (KN) counterparts to binary neutron star (BNS) and neutron star-black hole (NSBH) merger candidates. Here, we present a comprehensive study of the five high-significance (FAR < 1 per year) BNS and NSBH candidates in O4a. Our follow-up campaigns relied on both target-of-opportunity observations (ToO) and re-weighting of the nominal survey schedule to maximize coverage. We describe the toolkit we have been developing, Fritz, an instance of SkyPortal, instrumental in coordinating and managing our telescope scheduling, candidate vetting, and follow-up observations through a user-friendly interface. ZTF covered a total of 2841 deg$^2$ within the skymaps of the high-significance GW events, reaching a median depth of g~20.2 mag. We circulated 15 candidates, but found no viable KN counterpart to any of the GW events. Based on the ZTF non-detections of the high-significance events in O4a, we used a Bayesian approach, nimbus, to quantify the posterior probability of KN model parameters that are consistent with our non-detections. Our analysis favors KNe with initial absolute magnitude fainter than -16 mag. The joint posterior probability of a GW170817-like KN associated with all our O4a follow-ups was 64%. Additionally, we use a survey simulation software, simsurvey, to determine that our combined filtered efficiency to detect a GW170817-like KN is 36%, when considering the 5 confirmed astrophysical events in O3 (1 BNS and 4 NSBH), along with our O4a follow-ups. Following Kasliwal et al. (2020), we derived joint constraints on the underlying KN luminosity function based on our O3 and O4a follow-ups, determining that no more than 76% of KNe fading at 1 mag/day can peak at a magnitude brighter than -17.5 mag., Comment: submitted

Resting-state functional magnetic resonance imaging (rs-fMRI) is a noninvasive technique pivotal for understanding human neural mechanisms of intricate cognitive processes. Most rs-fMRI studies compute a single static functional connectivity matrix across brain regions of interest, or dynamic functional connectivity matrices with a sliding window approach. These approaches are at risk of oversimplifying brain dynamics and lack proper consideration of the goal at hand. While deep learning has gained substantial popularity for modeling complex relational data, its application to uncovering the spatiotemporal dynamics of the brain is still limited. We propose a novel interpretable deep learning framework that learns goal-specific functional connectivity matrix directly from time series and employs a specialized graph neural network for the final classification. Our model, DSAM, leverages temporal causal convolutional networks to capture the temporal dynamics in both low- and high-level feature representations, a temporal attention unit to identify important time points, a self-attention unit to construct the goal-specific connectivity matrix, and a novel variant of graph neural network to capture the spatial dynamics for downstream classification. To validate our approach, we conducted experiments on the Human Connectome Project dataset with 1075 samples to build and interpret the model for the classification of sex group, and the Adolescent Brain Cognitive Development Dataset with 8520 samples for independent testing. Compared our proposed framework with other state-of-art models, results suggested this novel approach goes beyond the assumption of a fixed connectivity matrix and provides evidence of goal-specific brain connectivity patterns, which opens up the potential to gain deeper insights into how the human brain adapts its functional connectivity specific to the task at hand., Comment: 18 Pages, 4 figures

We study the oblique propagation of weakly nonlinear dust-ion-acoustic (DIA) solitary waves (SWs) and shocks in collisional magnetized nonthermal dusty plasmas that are relevant in laboratory and space (Saturn's E-ring) environments. We consider plasmas to be composed of $q$-nonextensive hot electrons, thermal positive ions, and immobile negatively charged dust grains immersed in a static magnetic field and take into account the effects of ion creation (source), and ion loss (sink), ion-neutral and ion-dust collisions, anisotropic ion pressure and dust-charge fluctuations on the evolution of small-amplitude SWs and shocks. The ion-neutral collision enhancement equilibrium dust-charge number is self-consistently determined using Newton's Raphson method. We found that in laboratory dusty plasmas with adiabatic dust-charge variation [i.e., when the dust charging frequency ($\nu_{\rm{ch}}$) is much higher than the dust-plasma oscillation frequency ($\omega_{\rm{pd}}$)], the DIA solitary waves (DIASWs) get damped by the effects of the ion-dust and ion-neutral collisions, whereas the ion creation and ion loss leads to the amplification of solitary waves, and they appear as only compressive types with positive potential. On the other hand, in Saturn's E-ring plasmas, where the collisional and ion creation or ion loss effects are insignificant, the non-adiabaticity of dust-charge variation can give rise to the evolution of either damped DIASWs or DIA shocks, depending on the smallness of the ratios $\nu_{\rm{ch}}/\omega_{\rm{pd}}$ or $\omega_{\rm{pd}}/\nu_{\rm{ch}}$, respectively. Furthermore, two critical values of the nonextensive parameter $q$ exist, below (or above) which, the DIASWs and shocks can appear as rarefactive (or compressive) types. The characteristics of DIASWs and shocks are also analyzed numerically for parameters relevant to the laboratory and Saturn's E-ring plasmas., Comment: Total 19 pages and 21 Figures with some Figure number has subplots

Many frameworks for emotional text-to-speech (E-TTS) rely on human-annotated emotion labels that are often inaccurate and difficult to obtain. Learning emotional prosody implicitly presents a tough challenge due to the subjective nature of emotions. In this study, we propose a novel approach that leverages text awareness to acquire emotional styles without the need for explicit emotion labels or text prompts. We present TEMOTTS, a two-stage framework for E-TTS that is trained without emotion labels and is capable of inference without auxiliary inputs. Our proposed method performs knowledge transfer between the linguistic space learned by BERT and the emotional style space constructed by global style tokens. Our experimental results demonstrate the effectiveness of our proposed framework, showcasing improvements in emotional accuracy and naturalness. This is one of the first studies to leverage the emotional correlation between spoken content and expressive delivery for emotional TTS., Comment: Accepted at Speaker Odyssey 2024

A new study explores the distinct roles of spontaneous polarization and piezoelectric polarization in piezo-phototronic coupling. This investigation focuses on differences in photocatalytic and piezo-photocatalytic performance using sodium bismuth titanate (NBT), a key ferroelectric material. The research aims to identify which type of polarization has a greater influence on piezo-phototronic effects. A theoretical assessment complements the experimental findings, providing additional insights. This study explores the enhanced piezo-phototronic performance of electrospun nanofibers compared to sol-gel particles under different illumination conditions (11W UV, 250W UV, and natural sunlight). Electrospun nanofibers exhibited a rate constant (k) improvement of 2.5 to 3.75 times, whereas sol-gel particles showed only 1.3 to 1.4 times higher performance when ultrasonication was added to photocatalysis. Analysis using first-principle methods revealed that nanofibers had an elastic modulus (C33) about 2.15 times lower than sol-gel particles, indicating greater flexibility. The elongation of lattice along z-axis in the case of nanofibers reduced the covalency in the Bi-O and Ti-O bonds. These structural differences led to reduced spontaneous polarization and piezoelectric stress coefficients (e31 & e33). Despite having lower piezoelectric stress coefficients, higher flexibility in nanofibers led to a higher piezoelectric strain coefficient, 2.66 and 1.97 times greater than sol-gel particles, respectively. This improved the piezo-phototronic coupling for nanofibers.

Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is vital for fostering trust and comprehension in these models. This study investigates the impact of Saliency-guided Training (SGT) on model robustness, a technique aimed at improving the clarity of saliency maps to deepen understanding of the model's decision-making process. Experiments were conducted on standard benchmark datasets using various deep learning architectures trained with and without SGT. Findings demonstrate that SGT enhances both model robustness and interpretability. Additionally, we propose a novel approach combining SGT with standard adversarial training to achieve even greater robustness while preserving saliency map quality. Our strategy is grounded in the assumption that preserving salient features crucial for correctly classifying adversarial examples enhances model robustness, while masking non-relevant features improves interpretability. Our technique yields significant gains, achieving a 35\% and 20\% improvement in robustness against PGD attack with noise magnitudes of $0.2$ and $0.02$ for the MNIST and CIFAR-10 datasets, respectively, while producing high-quality saliency maps.

Purpose: Most studies evaluating artificial intelligence (AI) models that detect abnormalities in neuroimaging are either tested on unrepresentative patient cohorts or are insufficiently well-validated, leading to poor generalisability to real-world tasks. The aim was to determine the diagnostic test accuracy and summarise the evidence supporting the use of AI models performing first-line, high-volume neuroimaging tasks. Methods: Medline, Embase, Cochrane library and Web of Science were searched until September 2021 for studies that temporally or externally validated AI capable of detecting abnormalities in first-line CT or MR neuroimaging. A bivariate random-effects model was used for meta-analysis where appropriate. PROSPERO: CRD42021269563. Results: Only 16 studies were eligible for inclusion. Included studies were not compromised by unrepresentative datasets or inadequate validation methodology. Direct comparison with radiologists was available in 4/16 studies. 15/16 had a high risk of bias. Meta-analysis was only suitable for intracranial haemorrhage detection in CT imaging (10/16 studies), where AI systems had a pooled sensitivity and specificity 0.90 (95% CI 0.85 - 0.94) and 0.90 (95% CI 0.83 - 0.95) respectively. Other AI studies using CT and MRI detected target conditions other than haemorrhage (2/16), or multiple target conditions (4/16). Only 3/16 studies implemented AI in clinical pathways, either for pre-read triage or as post-read discrepancy identifiers. Conclusion: The paucity of eligible studies reflects that most abnormality detection AI studies were not adequately validated in representative clinical cohorts. The few studies describing how abnormality detection AI could impact patients and clinicians did not explore the full ramifications of clinical implementation.

We report direct measurements of the magnetic field screening at the limits of the Meissner phase for two superconducting Nb samples. The samples are processed with two different surface treatments that have been developed for superconducting radio-frequency cavity applications -- a "baseline" treatment and an oxygen-doping ("O-doping") treatment. The measurements show: 1) that the screening length is significantly longer in the "O-doping" sample compared to the "baseline" sample; 2) that the screening length near the limits of the Meissner phase increases with applied field; 3) the evolution of the screening profile as the material transitions from the Meissner phase to the mixed phase; and 4) a demonstration of the absence of any screening profile for the highest applied field, indicative of the full flux entering the sample. Measurements are performed utilizing the $\beta$-detected nuclear magnetic resonance ($\beta$-NMR) technique that allows depth resolved studies of the local magnetic field within the first 100 nm of the surface. The study takes advantage of the $\beta$-SRF beamline, a new facility at TRIUMF, Canada, where field levels up to 200 mT are available parallel to the sample surface to replicate radio frequency (RF) fields near the Meissner breakdown limits of Nb.

Semi-algebraic priors are ubiquitous in signal processing and machine learning. Prevalent examples include a) linear models where the signal lies in a low-dimensional subspace; b) sparse models where the signal can be represented by only a few coefficients under a suitable basis; and c) a large family of neural network generative models. In this paper, we prove a transversality theorem for semi-algebraic sets in orthogonal or unitary representations of groups: with a suitable dimension bound, a generic translate of any semi-algebraic set is transverse to the orbits of the group action. This, in turn, implies that if a signal lies in a low-dimensional semi-algebraic set, then it can be recovered uniquely from measurements that separate orbits. As an application, we consider the implications of the transversality theorem to the problem of recovering signals that are translated by random group actions from their second moment. As a special case, we discuss cryo-EM: a leading technology to constitute the spatial structure of biological molecules, which serves as our prime motivation. In particular, we derive explicit bounds for recovering a molecular structure from the second moment under a semi-algebraic prior and deduce information-theoretic implications. We also obtain information-theoretic bounds for three additional applications: factoring Gram matrices, multi-reference alignment, and phase retrieval. Finally, we deduce bounds for designing permutation invariant separators in machine learning.

In 5G, the Physical Downlink Control CHannel (PDCCH) carries crucial information enabling the User Equipment (UE) to connect in UL and DL. UEs are unaware of the frequency location at which PDCCH is encoded, hence they need to perform blind decoding over a limited set of possible candidates. We address the problem faced by the gNodeB of selecting PDCCH candidates for each UE to optimize data transmission. We formulate it as a Maximum Weighted Independent Set (MWIS) problem, that is known to be an NP-hard problem and cannot even be approximated. A solution method called Weight-to-Degree Ratio (WDR) Greedy emerges as a strong contender for practical implementations due to its favorable performance-to-complexity trade-off and theoretical performance guarantees.

Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning. Yet, the evaluations of these methods have primarily focused on the final output, such as changes in the accuracy of predicted classes, overlooking the issue of representational forgetting within the model. In this paper, we propose a novel representation-based evaluation framework for CL models. This approach involves gathering internal representations from throughout the continual learning process and formulating three-dimensional tensors. The tensors are formed by stacking representations, such as layer activations, generated from several inputs and model `snapshots', throughout the learning process. By conducting tensor component analysis (TCA), we aim to uncover meaningful patterns about how the internal representations evolve, expecting to highlight the merits or shortcomings of examined CL strategies. We conduct our analyses across different model architectures and importance-based continual learning strategies, with a curated task selection. While the results of our approach mirror the difference in performance of various CL strategies, we found that our methodology did not directly highlight specialized clusters of neurons, nor provide an immediate understanding the evolution of filters. We believe a scaled down version of our approach will provide insight into the benefits and pitfalls of using TCA to study continual learning dynamics.

The one loop inflation stemming from the superstring theory and associated Yukawa coupling arising from supersymmetric interactions is examined with CMB. The Yukawa coupling can exist beyond standard model particle physics sector. The tensor to scalar ratio of the loop inflation is found consistent with the recent CMB results for the Yukawa coupling from cosmology. The newly derived constraint on the Yukawa coupling constant may play a crucial role in validating inflationary model originating from supersymmetry and may shed some light on the formation of dark matter or dark energy. The outcomes of the study may be helpful in the phenomenological realisation of string theory., Comment: Title, abstract and introduction modified. 13 pages, 2 tables and 2 figures

Using small noise limit approach, we study degenerate stochastic ergodic control problems and as a byproduct obtain error bounds for the $\varepsilon$-optimal controls. We also establish tunneling for a special ergodic control problem and give a representation of the ergodic value using the tunneled Markov chain.

Cellular structures found in nature exhibit remarkable properties such as high strength, high energy absorption, excellent thermal/acoustic insulation, and fluid transfusion. Many of these structures are Voronoi-like; therefore researchers have proposed Voronoi multi-scale designs for a wide variety of engineering applications. However, designing such structures can be computationally prohibitive due to the multi-scale nature of the underlying analysis and optimization. In this work, we propose the use of a neural network (NN) to carry out efficient topology optimization (TO) of multi-scale Voronoi structures. The NN is first trained using Voronoi parameters (cell site locations, thickness, orientation, and anisotropy) to predict the homogenized constitutive properties. This network is then integrated into a conventional TO framework to minimize structural compliance subject to a volume constraint. Special considerations are given for ensuring positive definiteness of the constitutive matrix and promoting macroscale connectivity. Several numerical examples are provided to showcase the proposed method., Comment: Submitted to Engineering with Computers

We study the integrability of two-dimensional theories that are obtained by a dimensional reduction of certain four-dimensional gravitational theories describing the coupling of Maxwell fields and neutral scalar fields to gravity in the presence of a potential for the neutral scalar fields. By focusing on a certain solution subspace, we show that a subset of the equations of motion in two dimensions are the compatibility conditions for a modified version of the Breitenlohner-Maison linear system. Subsequently, we study the Liouville integrability of the 2D models encoding the chosen 4D solution subspace from a one-dimensional point of view by constructing Lax pair matrices. In this endeavour, we successfully employ a linear neural network to search for Lax pair matrices for these models, thereby illustrating how machine learning approaches can be effectively implemented to augment the identification of integrable structures in classical systems., Comment: 32 pages, 7 figures

In this work, we aim to improve transparency and efficacy in human-robot collaboration by developing machine teaching algorithms suitable for groups with varied learning capabilities. While previous approaches focused on tailored approaches for teaching individuals, our method teaches teams with various compositions of diverse learners using team belief representations to address personalization challenges within groups. We investigate various group teaching strategies, such as focusing on individual beliefs or the group's collective beliefs, and assess their impact on learning robot policies for different team compositions. Our findings reveal that team belief strategies yield less variation in learning duration and better accommodate diverse teams compared to individual belief strategies, suggesting their suitability in mixed-proficiency settings with limited resources. Conversely, individual belief strategies provide a more uniform knowledge level, particularly effective for homogeneously inexperienced groups. Our study indicates that the teaching strategy's efficacy is significantly influenced by team composition and learner proficiency, highlighting the importance of real-time assessment of learner proficiency and adapting teaching approaches based on learner proficiency for optimal teaching outcomes.

In recent times, the research on Large Language Models (LLMs) has grown exponentially, predominantly focusing on models underpinned by the transformer architecture, as established by [1], and further developed through the decoder-only variations by [2]. Contemporary efforts in this field primarily aim to enhance model capabilities by scaling up both the architecture and data volumes utilized during training. However, the exploration into reduce these model sizes while preserving their efficacy remains scant. In this study, we introduce three modifications to the decoder-only transformer architecture, namely ParallelGPT (pgpt), LinearGPT (lgpt), and ConvGPT (cgpt). These variants demonstrate comparable performance to the conventional architecture in language generation, yet benefit from reduced model sizes and faster training processes. We open-source the model weights and the complete codebase for these implementation for further research., Comment: 10 pages, 6 figures

LLMs have demonstrated significant potential in code generation tasks, achieving promising results at the function or statement level across various benchmarks. However, the complexities associated with creating code artifacts like classes, particularly within the context of real-world software repositories, remain underexplored. Prior research treats class-level generation as an isolated task, neglecting the intricate dependencies & interactions that characterize real-world software environments. To address this gap, we introduce RepoClassBench, a comprehensive benchmark designed to rigorously evaluate LLMs in generating complex, class-level code within real-world repositories. RepoClassBench includes "Natural Language to Class generation" tasks across Java, Python & C# from a selection of repositories. We ensure that each class in our dataset not only has cross-file dependencies within the repository but also includes corresponding test cases to verify its functionality. We find that current models struggle with the realistic challenges posed by our benchmark, primarily due to their limited exposure to relevant repository contexts. To address this shortcoming, we introduce Retrieve-Repotools-Reflect (RRR), a novel approach that equips LLMs with static analysis tools to iteratively navigate & reason about repository-level context in an agent-based framework. Our experiments demonstrate that RRR significantly outperforms existing baselines on RepoClassBench, showcasing its effectiveness across programming languages & under various settings. Our findings emphasize the critical need for code-generation benchmarks to incorporate repo-level dependencies to more accurately reflect the complexities of software development. Our work shows the benefits of leveraging specialized tools to enhance LLMs' understanding of repository context. We plan to make our dataset & evaluation harness public., Comment: Preprint with additional experiments

The vocabulary of language models in Gboard, Google's keyboard application, plays a crucial role for improving user experience. One way to improve the vocabulary is to discover frequently typed out-of-vocabulary (OOV) words on user devices. This task requires strong privacy protection due to the sensitive nature of user input data. In this report, we present a private OOV discovery algorithm for Gboard, which builds on recent advances in private federated analytics. The system offers local differential privacy (LDP) guarantees for user contributed words. With anonymous aggregation, the final released result would satisfy central differential privacy guarantees with $\varepsilon = 0.315, \delta = 10^{-10}$ for OOV discovery in en-US (English in United States).

The increasing growth of data volume, and the consequent explosion in demand for computational power, are affecting scientific computing, as shown by the rise of extreme data scientific workflows. As the need for computing power increases, quantum computing has been proposed as a way to deliver it. It may provide significant theoretical speedups for many scientific applications (i.e., molecular dynamics, quantum chemistry, combinatorial optimization, and machine learning). Therefore, integrating quantum computers into the computing continuum constitutes a promising way to speed up scientific computation. However, the scientific computing community still lacks the necessary tools and expertise to fully harness the power of quantum computers in the execution of complex applications such as scientific workflows. In this work, we describe the main characteristics of quantum computing and its main benefits for scientific applications, then we formalize hybrid quantum-classic workflows, explore how to identify quantum components and map them onto resources. We demonstrate concepts on a real use case and define a software architecture for a hybrid workflow management system.

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as a method to improve inference speed of language models by simultaneously predicting multiple future tokens, termed block drafts, which are subsequently verified and conditionally accepted by the autoregressive model. This paper contributes to the understanding and improvement of block drafts in two ways. First, we analyze the token distributions produced by multiple prediction heads. Secondly, we leverage this analysis to develop algorithms to improve BPD inference speed by refining the block drafts using n-gram and neural language models. Experiments demonstrate that refined block drafts yield a +5-21% increase in block efficiency (i.e., the number of accepted tokens from the block draft) across diverse datasets.

In this paper, we examine a multi-sensor system where each sensor may monitor more than one time-varying information process and send status updates to a remote monitor over a common channel. We consider that each sensor's status update may contain information about more than one information process in the system subject to the system's constraints. To investigate the impact of this correlation on the overall system's performance, we conduct an analysis of both the average Age of Information (AoI) and source state estimation error at the monitor. Building upon this analysis, we subsequently explore the impact of the packet arrivals, correlation probabilities, and rate of processes' state change on the system's performance. Next, we consider the case where sensors have limited sensing abilities and distribute a portion of their sensing abilities across the different processes. We optimize this distribution to minimize the total AoI of the system. Interestingly, we show that monitoring multiple processes from a single source may not always be beneficial. Our results also reveal that the optimal sensing distribution for diverse arrival rates may exhibit a rapid regime switch, rather than smooth transitions, after crossing critical system values. This highlights the importance of identifying these critical thresholds to ensure effective system performance.

Writer identification due to its widespread application in various fields has gained popularity over the years. In scenarios where optimum handwriting samples are available, whether they be in the form of a single line, a sentence, or an entire page, writer identification algorithms have demonstrated noteworthy levels of accuracy. However, in scenarios where only a limited number of handwritten samples are available, particularly in the form of word images, there is a significant scope for improvement. In this paper, we propose a writer identification system based on an attention-driven Convolutional Neural Network (CNN). The system is trained utilizing image segments, known as fragments, extracted from word images, employing a pyramid-based strategy. This methodology enables the system to capture a comprehensive representation of the data, encompassing both fine-grained details and coarse features across various levels of abstraction. These extracted fragments serve as the training data for the convolutional network, enabling it to learn a more robust representation compared to traditional convolution-based networks trained on word images. Additionally, the paper explores the integration of an attention mechanism to enhance the representational power of the learned features. The efficacy of the proposed algorithm is evaluated on three benchmark databases, demonstrating its proficiency in writer identification tasks, particularly in scenarios with limited access to handwriting data.

Federated Learning (FL) has garnered significant interest recently due to its potential as an effective solution for tackling many challenges in diverse application scenarios, for example, data privacy in network edge traffic classification. Despite its recognized advantages, FL encounters obstacles linked to statistical data heterogeneity and labeled data scarcity during the training of single-task models for machine learning-based traffic classification, leading to hindered learning performance. In response to these challenges, adopting a hard-parameter sharing multi-task learning model with auxiliary tasks proves to be a suitable approach. Such a model has the capability to reduce communication and computation costs, navigate statistical complexities inherent in FL contexts, and overcome labeled data scarcity by leveraging knowledge derived from interconnected auxiliary tasks. This paper introduces a new framework for federated auxiliary hard-parameter sharing multi-task learning, namely, FedAuxHMTL. The introduced framework incorporates model parameter exchanges between edge server and base stations, enabling base stations from distributed areas to participate in the FedAuxHMTL process and enhance the learning performance of the main task-network edge traffic classification. Empirical experiments are conducted to validate and demonstrate the FedAuxHMTL's effectiveness in terms of accuracy, total global loss, communication costs, computing time, and energy consumption compared to its counterparts.

Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot interaction and many more. Traditional supervised methods require large annotated datasets for training, which are expensive and time-consuming to acquire. This work proposes a novel approach using Cross-Architecture Pseudo-Labeling with contrastive learning for semi-supervised action recognition. Our framework leverages both labeled and unlabelled data to robustly learn action representations in videos, combining pseudo-labeling with contrastive learning for effective learning from both types of samples. We introduce a novel cross-architecture approach where 3D Convolutional Neural Networks (3D CNNs) and video transformers (VIT) are utilised to capture different aspects of action representations; hence we call it ActNetFormer. The 3D CNNs excel at capturing spatial features and local dependencies in the temporal domain, while VIT excels at capturing long-range dependencies across frames. By integrating these complementary architectures within the ActNetFormer framework, our approach can effectively capture both local and global contextual information of an action. This comprehensive representation learning enables the model to achieve better performance in semi-supervised action recognition tasks by leveraging the strengths of each of these architectures. Experimental results on standard action recognition datasets demonstrate that our approach performs better than the existing methods, achieving state-of-the-art performance with only a fraction of labeled data. The official website of this work is available at: https://github.com/rana2149/ActNetFormer., Comment: Submitted for peer review

In dynamic operational environments, particularly in collaborative robotics, the inevitability of failures necessitates robust and adaptable recovery strategies. Traditional automated recovery strategies, while effective for predefined scenarios, often lack the flexibility required for on-the-fly task management and adaptation to expected failures. Addressing this gap, we propose a novel approach that models recovery behaviors as adaptable robotic skills, leveraging the Behavior Trees and Motion Generators~(BTMG) framework for policy representation. This approach distinguishes itself by employing reinforcement learning~(RL) to dynamically refine recovery behavior parameters, enabling a tailored response to a wide array of failure scenarios with minimal human intervention. We assess our methodology through a series of progressively challenging scenarios within a peg-in-a-hole task, demonstrating the approach's effectiveness in enhancing operational efficiency and task success rates in collaborative robotics settings. We validate our approach using a dual-arm KUKA robot.

This paper presents the design of Variable-Pitch-Propeller mechanism and its application on a quadcopter called Heliquad to demonstrate its unique capabilities. The input-output relationship is estimated for a generic mechanism. Various singularities and actuator sizing requirements are also analyzed. The mechanism is manufactured, and the validated input-output relationship is implemented in the controller of Heliquad. Heliquad is controlled by a unified non-switching cascaded attitude-rate controller, followed by a unique Neural-Network-based reconfigurable control allocation to approximate nonlinear relationship between the control input and actuator command. The Heliquad prototype's mid-flight flip experiment validates the controller's tracking performance in upright as well as inverted conditions. The prototype is then flown in upright condition with only three of its working actuators. To the best of the authors' knowledge, the cambered airfoil propeller-equipped Heliquad prototype demonstrates full-attitude control, including yaw-rate, on three working actuators for the first time in the literature. Finally, the utility of this novel capability is demonstrated by safe recovery and precise landing post-mid-flight actuator failure crisis. Overall, the controller tracks the references well for all the experiments, and the output of the NN-based control allocation remains bounded throughout.

We examine the demographics of radio-emitting active galactic nuclei (AGN) in the local universe as a function of host galaxy properties, most notably both stellar mass and star formation rate. Radio AGN activity is theoretically implicated in helping reduce star formation rates of galaxies, and therefore it is natural to investigate the relationship between these two galaxy properties. We use a sample of around 10, 000 galaxies from the Mapping Nearby Galaxies at APO (MaNGA) survey, part of the Sloan Digital Sky Survey IV (SDSS-IV), along with the Faint Images of the Radio Sky at Twenty centimeters (FIRST) radio survey and the National Radio Astronomy Observatory (NRAO) Very Large Array (VLA) Sky Survey (NVSS). There are 1,126 galaxies in MaNGA with radio detections. Using star formation rate and stellar mass estimates based on Pipe3D, inferred from the high signal-to-noise ratio measurements from MaNGA, we show that star formation rates are strongly correlated with 20 cm radio emission, as expected. We identify as radio AGN those radio emitters that are much stronger than expected from the star formation rate. Using this sample of AGN, the well-measured stellar velocity dispersions from MaNGA, and the black hole M-sigma relationship, we examine the Eddington ratio distribution and its dependence on stellar mass and star formation rate. We find that the Eddington ratio distribution depends strongly on stellar mass, with more massive galaxies having larger Eddington ratios. As found in previous studies, the AGN fraction increases rapidly with stellar mass. We do not find any dependence on star formation rate, specific star formation rate, or velocity dispersion when controlling for stellar mass. We conclude that galaxy star formation rates appear to be unrelated to the presence or absence of a radio AGN, which may be useful in constraining theoretical models of AGN feedback.

We report the observation of a coalescing compact binary with component masses $2.5\text{-}4.5~M_\odot$ and $1.2\text{-}2.0~M_\odot$ (all measurements quoted at the 90% credible level). The gravitational-wave signal GW230529_181500 was observed during the fourth observing run of the LIGO-Virgo-KAGRA detector network on 2023 May 29 by the LIGO Livingston Observatory. The primary component of the source has a mass less than $5~M_\odot$ at 99% credibility. We cannot definitively determine from gravitational-wave data alone whether either component of the source is a neutron star or a black hole. However, given existing estimates of the maximum neutron star mass, we find the most probable interpretation of the source to be the coalescence of a neutron star with a black hole that has a mass between the most massive neutron stars and the least massive black holes observed in the Galaxy. We provisionally estimate a merger rate density of $55^{+127}_{-47}~\text{Gpc}^{-3}\,\text{yr}^{-1}$ for compact binary coalescences with properties similar to the source of GW230529_181500; assuming that the source is a neutron star-black hole merger, GW230529_181500-like sources constitute about 60% of the total merger rate inferred for neutron star-black hole coalescences. The discovery of this system implies an increase in the expected rate of neutron star-black hole mergers with electromagnetic counterparts and provides further evidence for compact objects existing within the purported lower mass gap., Comment: 45 pages (10 pages author list, 13 pages main text, 1 page acknowledgements, 13 pages appendices, 8 pages bibliography), 17 figures, 16 tables. Update to match version published in The Astrophysical Journal Letters. Data products available from https://zenodo.org/records/10845779

The 2023 AI4EIC hackathon was the culmination of the third annual AI4EIC workshop at The Catholic University of America. This workshop brought together researchers from physics, data science and computer science to discuss the latest developments in Artificial Intelligence (AI) and Machine Learning (ML) for the Electron Ion Collider (EIC), including applications for detectors, accelerators, and experimental control. The hackathon, held on the final day of the workshop, involved using a chatbot powered by a Large Language Model, ChatGPT-3.5, to train a binary classifier neutrons and photons in simulated data from the \textsc{GlueX} Barrel Calorimeter. In total, six teams of up to four participants from all over the world took part in this intense educational and research event. This article highlights the hackathon challenge, the resources and methodology used, and the results and insights gained from analyzing physics data using the most cutting-edge tools in AI/ML., Comment: 10 pages, 4 figures

Let $p$ denote a generative language model. Let $r$ denote a reward model that returns a scalar that captures the degree at which a draw from $p$ is preferred. The goal of language model alignment is to alter $p$ to a new distribution $\phi$ that results in a higher expected reward while keeping $\phi$ close to $p.$ A popular alignment method is the KL-constrained reinforcement learning (RL), which chooses a distribution $\phi_\Delta$ that maximizes $E_{\phi_{\Delta}} r(y)$ subject to a relative entropy constraint $KL(\phi_\Delta || p) \leq \Delta.$ Another simple alignment method is best-of-$N$, where $N$ samples are drawn from $p$ and one with highest reward is selected. In this paper, we offer a closed-form characterization of the optimal KL-constrained RL solution. We demonstrate that any alignment method that achieves a comparable trade-off between KL divergence and reward must approximate the optimal KL-constrained RL solution in terms of relative entropy. To further analyze the properties of alignment methods, we introduce two simplifying assumptions: we let the language model be memoryless, and the reward model be linear. Although these assumptions may not reflect complex real-world scenarios, they enable a precise characterization of the asymptotic behavior of both the best-of-$N$ alignment, and the KL-constrained RL method, in terms of information-theoretic quantities. We prove that the reward of the optimal KL-constrained RL solution satisfies a large deviation principle, and we fully characterize its rate function. We also show that the rate of growth of the scaled cumulants of the reward is characterized by a proper Renyi cross entropy. Finally, we show that best-of-$N$ is asymptotically equivalent to KL-constrained RL solution by proving that their expected rewards are asymptotically equal, and concluding that the two distributions must be close in KL divergence.

Functional programs typically interact with stateful libraries that hide state behind typed abstractions. One particularly important class of applications are data structure implementations that rely on such libraries to provide a level of efficiency and scalability that may be otherwise difficult to achieve. However, because the specifications of the methods provided by these libraries are necessarily general and rarely specialized to the needs of any specific client, any required application-level invariants must often be expressed in terms of additional constraints on the (often) opaque state maintained by the library. In this paper, we consider the specification and verification of such representation invariants using symbolic finite automata (SFA). We show that SFAs can be used to succinctly and precisely capture fine-grained temporal and data-dependent histories of interactions between functional clients and stateful libraries. To facilitate modular and compositional reasoning, we integrate SFAs into a refinement type system to qualify stateful computations resulting from such interactions. The particular instantiation we consider, Hoare Automata Types (HATs), allows us to both specify and automatically type-check the representation invariants of a datatype, even when its implementation depends on stateful library methods that operate over hidden state. We also develop a new bidirectional type checking algorithm that implements an efficient subtyping inclusion check over HATs, enabling their translation into a form amenable for SMT-based automated verification. We present extensive experimental results on an implementation of this algorithm that demonstrates the feasibility of type-checking complex and sophisticated HAT-specified OCaml data structure implementations., Comment: PLDI'24

This study examines the effects of macroeconomic policies on financial markets using a novel approach that combines Machine Learning (ML) techniques and causal inference. It focuses on the effect of interest rate changes made by the US Federal Reserve System (FRS) on the returns of fixed income and equity funds between January 1986 and December 2021. The analysis makes a distinction between actively and passively managed funds, hypothesizing that the latter are less susceptible to changes in interest rates. The study contrasts gradient boosting and linear regression models using the Double Machine Learning (DML) framework, which supports a variety of statistical learning techniques. Results indicate that gradient boosting is a useful tool for predicting fund returns; for example, a 1% increase in interest rates causes an actively managed fund's return to decrease by -11.97%. This understanding of the relationship between interest rates and fund performance provides opportunities for additional research and insightful, data-driven advice for fund managers and investors

Video games have played a crucial role in entertainment since their development in the 1970s, becoming even more prominent during the lockdown period when people were looking for ways to entertain them. However, at that time, players were unaware of the significant impact that playtime could have on their feelings. This has made it challenging for designers and developers to create new games since they have to control the emotional impact that these games will take on players. Thus, the purpose of this study is to look at how a player's emotions are affected by the duration of the game. In order to achieve this goal, a framework for emotion detection is created. According to the experiment's results, the volunteers' general ability to express emotions increased from 20 to 60 minutes. In comparison to shorter gameplay sessions, the experiment found that extended gameplay sessions did significantly affect the player's emotions. According to the results, it was recommended that in order to lessen the potential emotional impact that playing computer and video games may have in the future, game producers should think about creating shorter, entertaining games.

Data-driven neural path planners are attracting increasing interest in the robotics community. However, their neural network components typically come as black boxes, obscuring their underlying decision-making processes. Their black-box nature exposes them to the risk of being compromised via the insertion of hidden malicious behaviors. For example, an attacker may hide behaviors that, when triggered, hijack a delivery robot by guiding it to a specific (albeit wrong) destination, trapping it in a predefined region, or inducing unnecessary energy expenditure by causing the robot to repeatedly circle a region. In this paper, we propose a novel approach to specify and inject a range of hidden malicious behaviors, known as backdoors, into neural path planners. Our approach provides a concise but flexible way to define these behaviors, and we show that hidden behaviors can be triggered by slight perturbations (e.g., inserting a tiny unnoticeable object), that can nonetheless significantly compromise their integrity. We also discuss potential techniques to identify these backdoors aimed at alleviating such risks. We demonstrate our approach on both sampling-based and search-based neural path planners.

We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models. Although existing works showed that watermarking can be robust for natural language, we show that it is easy to remove these watermarks on code by semantic-preserving transformations.