Search

Material discovery is a cornerstone of modern science, driving advancements in diverse disciplines from biomedical technology to climate solutions. Predicting synthesizability, a critical factor in realizing novel materials, remains a complex challenge due to the limitations of traditional heuristics and thermodynamic proxies. While stability metrics such as formation energy offer partial insights, they fail to account for kinetic factors and technological constraints that influence synthesis outcomes. These challenges are further compounded by the scarcity of negative data, as failed synthesis attempts are often unpublished or context-specific. We present SynCoTrain, a semi-supervised machine learning model designed to predict the synthesizability of materials. SynCoTrain employs a co-training framework leveraging two complementary graph convolutional neural networks: SchNet and ALIGNN. By iteratively exchanging predictions between classifiers, SynCoTrain mitigates model bias and enhances generalizability. Our approach uses Positive and Unlabeled (PU) Learning to address the absence of explicit negative data, iteratively refining predictions through collaborative learning. The model demonstrates robust performance, achieving high recall on internal and leave-out test sets. By focusing on oxide crystals, a well-characterized material family with extensive experimental data, we establish SynCoTrain as a reliable tool for predicting synthesizability while balancing dataset variability and computational efficiency. This work highlights the potential of co-training to advance high-throughput materials discovery and generative research, offering a scalable solution to the challenge of synthesizability prediction.

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of LLMs through BitMoD, an algorithm-hardware co-design solution that enables efficient LLM acceleration at low weight precision. On the algorithm side, BitMoD introduces fine-grained data type adaptation that uses a different numerical data type to quantize a group of (e.g., 128) weights. Through the careful design of these new data types, BitMoD is able to quantize LLM weights to very low precision (e.g., 4 bits and 3 bits) while maintaining high accuracy. On the hardware side, BitMoD employs a bit-serial processing element to easily support multiple numerical precisions and data types; our hardware design includes two key innovations: First, it employs a unified representation to process different weight data types, thus reducing the hardware cost. Second, it adopts a bit-serial dequantization unit to rescale the per-group partial sum with minimal hardware overhead. Our evaluation on six representative LLMs demonstrates that BitMoD significantly outperforms state-of-the-art LLM quantization and acceleration methods. For discriminative tasks, BitMoD can quantize LLM weights to 4-bit with $<\!0.5\%$ accuracy loss on average. For generative tasks, BitMoD is able to quantize LLM weights to 3-bit while achieving better perplexity than prior LLM quantization scheme. Combining the superior model performance with an efficient accelerator design, BitMoD achieves an average of $1.69\times$ and $1.48\times$ speedups compared to prior LLM accelerators ANT and OliVe, respectively., Comment: HPCA 2025

From the study of the high order freeness of random matrices, it is known that the order $r$ cumulant of the trace of a polynomial of $N$-dimensional GUE/GOE is of order $N^{2-r}$ if $r$ is fixed. In this work, we extend the study along three directions. First, we also consider generally distributed Wigner matrices with subexponential entries. Second, we include the deterministic matrices into discussion and consider arbitrary polynomials in random matrices and deterministic matrices. Third, more importantly, we consider the ultra high order cumulants in the sense that $r$ is arbitrary, i.e., could be $N$ dependent. Our main results are the upper bounds of the ultra high order cumulants, for which not only the $N$-dependence but also the $r$-dependence become significant. These results are then used to derive three types of quantitative CLT for the trace of any given self-adjoint polynomial in these random matrix variables: a CLT with a Cram\'{e}r type correction, a Berry-Esseen bound, and a concentration inequality which captures both the Gaussian tail in the small deviation regime and $M$-dependent tail in the large deviation regime, where $M$ is the degree of the polynomial. In contrast to the second order freeness which implies the CLT for linear eigenvalue statistics of polynomials in random matrices, our study on the ultra high order cumulants leads to the quantitative versions of the CLT.

We report on tip-enhanced Raman scattering (TERS) of H2 and D2 molecules physisorbed within a plasmonic picocavity at a cryogenic temperature (10 K). The intense Raman peaks resulting from the rotational and vibrational transitions are observed at sub-nanometer gap distances of the junction formed by a Ag tip and Ag(111) surface. We clarify that the predominant contribution of the electromagnetic field enhancement of the picocavity to the detection of a single hydrogen molecule. The gap-distance dependent TERS reveals not only the evolution of the picocavity field, but also the interaction between the molecule and tip/surface, which exhibit nontrivial isotope effects. A significant red-shift and peak broadening of the H-H stretching as the gap distance decreases, while the D-D stretching mode is unaffected. A combination of density functional theory and reduced-dimension models reveals that a distinct anharmonicity in the mode potential of H2 is one cause of the anomalous red-shift, whereas D2 has less anharmonicity due to the geometric isotope effect.

Human Mesh Recovery (HMR) is an important yet challenging problem with applications across various domains including motion capture, augmented reality, and biomechanics. Accurately predicting human pose parameters from a single image remains a challenging 3D computer vision task. In this work, we introduce DeforHMR, a novel regression-based monocular HMR framework designed to enhance the prediction of human pose parameters using deformable attention transformers. DeforHMR leverages a novel query-agnostic deformable cross-attention mechanism within the transformer decoder to effectively regress the visual features extracted from a frozen pretrained vision transformer (ViT) encoder. The proposed deformable cross-attention mechanism allows the model to attend to relevant spatial features more flexibly and in a data-dependent manner. Equipped with a transformer decoder capable of spatially-nuanced attention, DeforHMR achieves state-of-the-art performance for single-frame regression-based methods on the widely used 3D HMR benchmarks 3DPW and RICH. By pushing the boundary on the field of 3D human mesh recovery through deformable attention, we introduce an new, effective paradigm for decoding local spatial information from large pretrained vision encoders in computer vision., Comment: 11 pages, 5 figures, 3DV2025

Over many decades fully nonlinear PDEs, and the complex Monge-Amp\`ere equation in particular played a central role in the study of complex manifolds. Most previous works focused on problems that can be expressed through equations involving real $(1, 1)$ forms. As many important questions, especially those linked to higher cohomology classes in complex geometry involve real $(p, p)$ forms for $p > 1$, there is a strong need to develop PDE techniques to study them. In this paper we consider a fully nonlinear equation for $(p, p)$ forms on compact Hermitian manifolds. We establish the existence of classical solutions for a large class of these equations by a parabolic approach, proving the long-time existence and convergence of solutions to the elliptic case.

Reinforcement learning algorithms are usually stated without theoretical guarantees regarding their performance. Recently, Jin, Yang, Wang, and Jordan (COLT 2020) showed a polynomial-time reinforcement learning algorithm (namely, LSVI-UCB) for the setting of linear Markov decision processes, and provided theoretical guarantees regarding its running time and regret. In real-world scenarios, however, the space usage of this algorithm can be prohibitive due to a utilized linear regression step. We propose and analyze two modifications of LSVI-UCB, which alternate periods of learning and not-learning, to reduce space and time usage while maintaining sublinear regret. We show experimentally, on synthetic data and real-world benchmarks, that our algorithms achieve low space usage and running time, while not significantly sacrificing regret., Comment: 27 pages, 9 figures

Tidal disruption events (TDEs) result from stars being gravitationally-scattered into low angular momentum orbits around massive black holes. We show that the short lifetimes of massive Population III stars at high redshifts could significantly suppress the volumetric TDE rate because they are too short-lived to reach disruption-fated orbits. However, this suppression can be alleviated if captured dark matter (DM) within stellar interiors provides an additional energy source, thereby extending stellar lifetimes. We find that this TDE rate revival is most pronounced for DM particles with mass $\mathcal{O}({\rm MeV})$, as this particle mass scale is optimal in the competing processes of DM accretion and evaporation in stars., Comment: 4+1 pages, 3+1 figures. Comments are welcome

Interactive sensors are an important component of robotic systems but often require manual replacement due to wear and tear. Automating this process can enhance system autonomy and facilitate long-term deployment. We developed an autonomous sensor exchange and calibration system for an agriculture crop monitoring robot that inserts a nitrate sensor into cornstalks. A novel gripper and replacement mechanism, featuring a reliable funneling design, were developed to enable efficient and reliable sensor exchanges. To maintain consistent nitrate sensor measurement, an on-board sensor calibration station was integrated to provide in-field sensor cleaning and calibration. The system was deployed at the Ames Curtis Farm in June 2024, where it successfully inserted nitrate sensors with high accuracy into 30 cornstalks with a 77$\%$ success rate.

Artificial Intelligence models encoding biology and chemistry are opening new routes to high-throughput and high-quality in-silico drug development. However, their training increasingly relies on computational scale, with recent protein language models (pLM) training on hundreds of graphical processing units (GPUs). We introduce the BioNeMo Framework to facilitate the training of computational biology and chemistry AI models across hundreds of GPUs. Its modular design allows the integration of individual components, such as data loaders, into existing workflows and is open to community contributions. We detail technical features of the BioNeMo Framework through use cases such as pLM pre-training and fine-tuning. On 256 NVIDIA A100s, BioNeMo Framework trains a three billion parameter BERT-based pLM on over one trillion tokens in 4.2 days. The BioNeMo Framework is open-source and free for everyone to use.

In this article, we propose the integration of the Holographic Multiple Input Multiple Output (HMIMO) as a transformative solution for next generation Non-Terrestrial Networks (NTNs), addressing key challenges, such as high hardware costs, launch expenses, and energy inefficiency. Traditional NTNs are constrained by the financial and operational limitations posed by bulky, costly antenna systems, alongside the complexities of maintaining effective communications in space. HMIMO offers a novel approach utilizing compact and lightweight arrays of densely packed radiating elements with real-time reconfiguration capabilities, thus, capable of optimizing system performance under dynamic conditions such as varying orbital dynamics and Doppler shifts. By replacing conventional antenna systems with HMIMO, the complexity and cost of satellite manufacturing and launch can be substantially reduced, enabling more streamlined and cost-effective satellite designs. This advancement holds significant potential to democratize space communications, making them accessible to a broader range of stakeholders, including smaller nations and commercial enterprises. Moreover, the inherent capabilities of HMIMO in enhancing energy efficiency, scalability, and adaptability position this technology as a key enabler of new use cases and sustainable satellite operations.

Neoadjuvant chemotherapy (NAC) response prediction for triple negative breast cancer (TNBC) patients is a challenging task clinically as it requires understanding complex histology interactions within the tumor microenvironment (TME). Digital whole slide images (WSIs) capture detailed tissue information, but their giga-pixel size necessitates computational methods based on multiple instance learning, which typically analyze small, isolated image tiles without the spatial context of the TME. To address this limitation and incorporate TME spatial histology interactions in predicting NAC response for TNBC patients, we developed a histology context-aware transformer graph convolution network (NACNet). Our deep learning method identifies the histopathological labels on individual image tiles from WSIs, constructs a spatial TME graph, and represents each node with features derived from tissue texture and social network analysis. It predicts NAC response using a transformer graph convolution network model enhanced with graph isomorphism network layers. We evaluate our method with WSIs of a cohort of TNBC patient (N=105) and compared its performance with multiple state-of-the-art machine learning and deep learning models, including both graph and non-graph approaches. Our NACNet achieves 90.0% accuracy, 96.0% sensitivity, 88.0% specificity, and an AUC of 0.82, through eight-fold cross-validation, outperforming baseline models. These comprehensive experimental results suggest that NACNet holds strong potential for stratifying TNBC patients by NAC response, thereby helping to prevent overtreatment, improve patient quality of life, reduce treatment cost, and enhance clinical outcomes, marking an important advancement toward personalized breast cancer treatment., Comment: This paper is accepted by Computerized Medical Imaging and Graphics (Nov 07 2024)

Importance sampling and independent Metropolis-Hastings (IMH) are among the fundamental building blocks of Monte Carlo methods. Both require a proposal distribution that globally approximates the target distribution. The Radon-Nikodym derivative of the target distribution relative to the proposal is called the weight function. Under the weak assumption that the weight is unbounded but has a number of finite moments under the proposal distribution, we obtain new results on the approximation error of importance sampling and of the particle independent Metropolis-Hastings algorithm (PIMH), which includes IMH as a special case. For IMH and PIMH, we show that the common random numbers coupling is maximal. Using that coupling we derive bounds on the total variation distance of a PIMH chain to the target distribution. The bounds are sharp with respect to the number of particles and the number of iterations. Our results allow a formal comparison of the finite-time biases of importance sampling and IMH. We further consider bias removal techniques using couplings of PIMH, and provide conditions under which the resulting unbiased estimators have finite moments. We compare the asymptotic efficiency of regular and unbiased importance sampling estimators as the number of particles goes to infinity., Comment: 35 pages including the proofs in appendices

A Reconfigurable Intelligent Surface (RIS) can significantly enhance network positioning and mapping, acting as an additional anchor point in the reference system and improving signal strength and measurement diversity through the generation of favorable scattering conditions and virtual line-of-sight paths. In this paper, we present a comprehensive framework aimed at user localization and scatterer position estimation in an indoor environment with multipath effects. Our approach leverages beam sweeping through codebook-based beamforming at an 1-bit RIS to scan the environment, applies signal component extraction mechanisms, and utilizes a super-resolution algorithm for angle-based positioning of both connected users and scatterers. To validate the system's effectiveness, accurate 3D ray tracing models are employed, ensuring the robustness and effectiveness of the proposed approach in practical scenarios., Comment: 6 pages, 4 figures, to be presented in an ESA workshop

This paper presents an optimization framework for near-field localization with Dynamic Metasurface Antenna (DMA) receivers. This metasurface technology offers enhanced angular and range resolution realizing efficient hybrid Analog and Digital (A/D) BeamForming (BF) with sub-wavelength-spaced metamaterials of tunable responses. However, the vast majority of the state-of-the-art DMA designs is based on an idealized model for their reception operation, which neglects several practical aspects, such as the inevitable mutual coupling among the densely deployed metamaterials within a given aperture. Capitalizing on a recent circuit-compliant active metasurface model, we present a novel mutual-coupling-aware framework for localization-optimized hybrid A/D BF weights at the reception DMA. To deal with the intrinsic complexity of the deployed model, we introduce first- and second-order approximations for the DMA analog BF matrix that enable efficient optimization, while maintaining accuracy. We derive the Cramer-Rao Bound for the user position estimation which serves as our design objective for the hybrid A/D BF matrices. Closed-form solutions for these matrices for both approximations are presented, whose validity is confirmed via numerical investigations. It is also demonstrated that the proposed DMA design outperforms state-of-the-art multi-antenna reception architectures optimized for the same localization objective.

Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop characteristics. We present a robotic system for autonomous pepper harvesting designed to operate in these unprotected, complex settings. Utilizing a custom handheld shear-gripper, we collected 300 demonstrations to train a visuomotor policy, enabling the system to adapt to varying field conditions and crop diversity. We achieved a success rate of 28.95% with a cycle time of 31.71 seconds, comparable to existing systems tested under more controlled conditions like greenhouses. Our system demonstrates the feasibility and effectiveness of leveraging imitation learning for automated harvesting in unstructured agricultural environments. This work aims to advance scalable, automated robotic solutions for agriculture in natural settings., Comment: 8 pages, 11 figures

The influence of growth regimes of the silicon capping layer on the optical properties of heterostructures with submonolayer InAs quantum dots embedded in a silicon matrix has been studied. The photoluminescence signal at 1650 nm from submonolayer quantum dots at low temperatures up to 120 K was obtained. It was established that the use of a two-stage method of silicon overgrowing InAs nanoislands makes it possible to increase the photoluminescence intensity by improving the crystalline quality of heterostructures. Analysis of the temperature dependence allowed us to calculate an activation energy for electrons confined in the quantum dots potential well at the level of the thermal energy at room temperature., Comment: 22 pages, in Russian language, 4 figures

Topic modeling, or more broadly, dimensionality reduction, techniques provide powerful tools for uncovering patterns in large datasets and are widely applied across various domains. We investigate how Non-negative Matrix Factorization (NMF) can introduce bias in the representation of data groups, such as those defined by demographics or protected attributes. We present an approach, called Fairer-NMF, that seeks to minimize the maximum reconstruction loss for different groups relative to their size and intrinsic complexity. Further, we present two algorithms for solving this problem. The first is an alternating minimization (AM) scheme and the second is a multiplicative updates (MU) scheme which demonstrates a reduced computational time compared to AM while still achieving similar performance. Lastly, we present numerical experiments on synthetic and real datasets to evaluate the overall performance and trade-offs of Fairer-NMF

When turbulent boundary layer flows encounter abrupt roughness changes, an Internal Boundary Layer (IBL) forms. Equilibrium theory breaks down in the nonequilibrium IBL, which may extend O(10) km for natural atmospheric flows. Here, we find that the IBL possesses a characteristic time-scale associated with the IBL height, ${\delta}_i$. We show that ${\delta}_i$ and the edge velocity set the scales of the mean and defect velocity profiles within the IBL, for simulation and experimental data covering a multitude of roughness transition types. We present a nontrivial extension of equilibrium theory to the dynamically adjusting IBL, which can be useful for modeling a range of environmental and industrial flows., Comment: 6 Pages, 4 Figures

Cognitive radio (CR) networks face significant challenges in spectrum sensing, especially under spectrum scarcity. Fluid antenna systems (FAS) can offer an unorthodox solution due to their ability to dynamically adjust antenna positions for improved channel gain. In this letter, we study a FAS-driven CR setup where a secondary user (SU) adjusts the positions of fluid antennas to detect signals from the primary user (PU). We aim to maximize the detection probability under the constraints of the false alarm probability and the received beamforming of the SU. To address this problem, we first derive a closed-form expression for the optimal detection threshold and reformulate the problem to find its solution. Then an alternating optimization (AO) scheme is proposed to decompose the problem into several sub-problems, addressing both the received beamforming and the antenna positions at the SU. The beamforming subproblem is addressed using a closed-form solution, while the fluid antenna positions are solved by successive convex approximation (SCA). Simulation results reveal that the proposed algorithm provides significant improvements over traditional fixed-position antenna (FPA) schemes in terms of spectrum sensing performance.

Model order reduction (MOR) is essential in integrated circuit design, particularly when dealing with large-scale electromagnetic models extracted from complex designs. The numerous passive elements introduced in these models pose significant challenges in the simulation process. MOR methods based on balanced truncation (BT) help address these challenges by producing compact reduced-order models (ROMs) that preserve the original model's input-output port behavior. In this work, we present an extended Krylov subspace-based BT approach with a frequency-aware convergence criterion and efficient implementation techniques for reducing large-scale models. Experimental results indicate that our method generates accurate and compact ROMs while achieving up to x22 smaller ROMs with similar accuracy compared to ANSYS RaptorX ROMs for large-scale benchmarks., Comment: arXiv admin note: substantial text overlap with arXiv:2311.08478

In this paper we create a definition for prime gaps in the Gaussian integers using a boxcar metric. From this we used numerical methods to derive an asymptotic upper bound for the gaps in this scenario, namely O(log^2|p_{n}|).

Tiltrotors are an aircraft concept with the ability to rotate their rotors freely, achieving vertical take-off and fast forward flight. The combination of helicopter and fixed-wing flight into one aircraft provides versatility in mission selection, yet challenges persist in their construction and control. Tiltrotor aircraft can operate in three primary modes: helicopter, fixed-wing, and transition, with the transition mode facilitating the shift between helicopter and fixed-wing flight. However, control within this transition region is inherently challenging due to its non-linear nature, hence tiltrotors have been predominantly limited to military applications. Thus, this paper aims to explore transition mode control for a large-size tiltrotor aircraft, tailored to civil applications. A novel, large-sized, tiltrotor concept is presented, accompanied by a derived mathematical model describing the aircrafts behaviours. A PID control method has been used to control the height, pitch, and velocity variations within the transition mode with secondary control loop developed to control the tilt angle during transition. The derived model and control are then implemented within a MATLAB simulation, where the control method was iterated to improve performance. The results show a full transition was achieved in under 14 seconds, where altitude variations were kept below 10 metres. Though the transition mode control was successful, a collective look at the data showcases issues with assumptions as well as thrust discontinuities. The implications of these results are discussed, with suggested improvements proposed for future work.

Spiking neural networks (SNNs) represent a promising approach in machine learning, combining the hierarchical learning capabilities of deep neural networks with the energy efficiency of spike-based computations. Traditional end-to-end training of SNNs is often based on back-propagation, where weight updates are derived from gradients computed through the chain rule. However, this method encounters challenges due to its limited biological plausibility and inefficiencies on neuromorphic hardware. In this study, we introduce an alternative training approach for SNNs. Instead of using back-propagation, we leverage weight perturbation methods within a forward-mode gradient framework. Specifically, we perturb the weight matrix with a small noise term and estimate gradients by observing the changes in the network output. Experimental results on regression tasks, including solving various PDEs, show that our approach achieves competitive accuracy, suggesting its suitability for neuromorphic systems and potential hardware compatibility.

We report the discovery of a unique quasar-dusty star-forming galaxy (DSFG) system at $z = 5.63$, consisting of the bright quasar J1133+1603 ($M_{\rm UV} = -27.42$) and its compact, dust-obscured companion, J1133c. ALMA observations reveal a prominent [C II] bridge connecting the quasar and DSFG, indicating ongoing interaction at a projected separation of 1.8 arcsec ($\sim$10 proper kpc). J1133c exhibits unusually bright and broad [C II] emission ($L_{\rm [CII]} > 10^{43}$ erg s$^{-1}$, FWHM $> 500$ km s$^{-1}$), with a [C II] luminosity five times that of the quasar, suggesting intense star formation or potential AGN activity. The inferred star formation rate from [C II] is approximately $10^3$ M$_\odot$ yr$^{-1}$. The remarkable properties of this pair strongly suggest that galaxy interactions may simultaneously trigger both starburst and quasar activity, driving rapid evolution in the early universe., Comment: RNAAS; 4 pages, 1 figure; comments welcome

The intense magnetic fields of neutron stars naturally lead to strong anisotropy and polarization of radiation emanating from their surfaces, both being sensitive to the hot spot position on the surface. Accordingly, pulse phase-resolved intensities and polarizations depend on the angle between the magnetic and spin axes and the observer's viewing direction. In this paper, results are presented from a Monte Carlo simulation of neutron star atmospheres that uses a complex electric field vector formalism to treat polarized radiative transfer due to magnetic Thomson scattering. General relativistic influences on the propagation of light from the stellar surface to a distant observer are taken into account. The paper outlines a range of theoretical predictions for pulse profiles at different X-ray energies, focusing on magnetars and also neutron stars of lower magnetization. By comparing these models with observed intensity and polarization pulse profiles for the magnetar 1RXS J1708-40, and the light curve for the pulsar PSR J0821-4300, constraints on the stellar geometry angles and the size of putative polar cap hot spots are obtained., Comment: 6 pages, 3 figures, accepted for publication in Astronomische Nachrichten in the special issue for the XMM-Newton 2024 Science Workshop: The X-Ray Mysteries of Neutron Stars and White Dwarfs

Usual parametric and semi-parametric regression methods are inappropriate and inadequate for large clustered survival studies when the appropriate functional forms of the covariates and their interactions in hazard functions are unknown, and random cluster effects and cluster-level covariates are spatially correlated. We present a general nonparametric method for such studies under the Bayesian ensemble learning paradigm called Soft Bayesian Additive Regression Trees. Our methodological and computational challenges include large number of clusters, variable cluster sizes, and proper statistical augmentation of the unobservable cluster-level covariate using a data registry different from the main survival study. We use an innovative 3-step approach based on latent variables to address our computational challenges. We illustrate our method and its advantages over existing methods by assessing the impacts of intervention in some county-level and patient-level covariates to mitigate existing racial disparity in breast cancer survival in 67 Florida counties (clusters) using two different data resources. Florida Cancer Registry (FCR) is used to obtain clustered survival data with patient-level covariates, and the Behavioral Risk Factor Surveillance Survey (BRFSS) is used to obtain further data information on an unobservable county-level covariate of Screening Mammography Utilization (SMU).

In our demo, participants are invited to explore the Diff-MSTC prototype, which integrates the Diff-MST model into Steinberg's digital audio workstation (DAW), Cubase. Diff-MST, a deep learning model for mixing style transfer, forecasts mixing console parameters for tracks using a reference song. The system processes up to 20 raw tracks along with a reference song to predict mixing console parameters that can be used to create an initial mix. Users have the option to manually adjust these parameters further for greater control. In contrast to earlier deep learning systems that are limited to research ideas, Diff-MSTC is a first-of-its-kind prototype integrated into a DAW. This integration facilitates mixing decisions on multitracks and lets users input context through a reference song, followed by fine-tuning of audio effects in a traditional manner., Comment: Presented at 2024 International Society for Music Information Retrieval

A complex Monge-Amp\`ere equation for differential $(p,p)$ forms is introduced on compact K\"ahler manifolds. For any $1 \leq p < n$, we show the existence of smooth solutions unique up to adding constants. For $p=1$, this corresponds to the Calabi-Yau theorem proved by S. T. Yau, and for $p=n-1$, this gives the Monge-Amp\`ere equation for $(n-1)$ plurisubharmonic functions solved by Tosatti-Weinkove. For other $p$ values, this defines a non-linear PDE that falls outside of the general framework of Caffarelli-Nirenberg-Spruck. Further, we define a geometric flow for higher-order forms that preserves their cohomology classes, and extends the K\"ahler-Ricci flow naturally to $(p,p)$ forms. As a consequence of our main theorem, we show that this flow exists in a maximal time interval and can be shown to converge under some assumptions. A modified flow is introduced in order to study the evolution of Hodge classes of $M$ with respect to the rational span of Chern classes of holomoprhic vector bundles. The convergence of the associated normalized flow is shown and some potential applications are discussed.

In this paper, we derive a new Kalman filter with probabilistic data association between measurements and states. We formulate a variational inference problem to approximate the posterior density of the state conditioned on the measurement data. We view the unknown data association as a latent variable and apply Expectation Maximization (EM) to obtain a filter with update step in the same form as the Kalman filter but with expanded measurement vector of all potential associations. We show that the association probabilities can be computed as permanents of matrices with measurement likelihood entries. We also propose an ambiguity check that associates only a subset of ambiguous measurements and states probabilistically, thus reducing the association time and preventing low-probability measurements from harming the estimation accuracy. Experiments in simulation show that our filter achieves lower tracking errors than the well-established joint probabilistic data association filter (JPDAF), while running at comparable rate. We also demonstrate the effectiveness of our filter in multi-object tracking (MOT) on multiple real-world datasets, including MOT17, MOT20, and DanceTrack. We achieve better higher order tracking accuracy (HOTA) than previous Kalman-filter methods and remain real-time. Associating only bounding boxes without deep features or velocities, our method ranks top-10 on both MOT17 and MOT20 in terms of HOTA. Given offline detections, our algorithm tracks at 250+ fps on a single laptop CPU. Code is available at https://github.com/hwcao17/pkf.

Advances in Autonomous Underwater Vehicles (AUVs) have evolved vastly in short period of time. While advancements in sonar and camera technology with deep learning aid the obstacle detection and path planning to a great extent, achieving the right balance between computational resources , precision and safety maintained remains a challenge. Finding optimal solutions for real-time navigation in cluttered environments becomes pivotal as systems have to process large amounts of data efficiently. In this work, we propose a novel obstacle avoidance method for navigating 3D underwater environments. This approach utilizes a standard multibeam forward-looking sonar to detect and map obstacle in 3D environment. Instead of using computationally expensive 3D sensors, we pivot the 2D sonar to get 3D heuristic data effectively transforming the sensor into a 2.5D sonar for real-time 3D navigation decisions. This approach enhances obstacle detection and navigation by leveraging the simplicity of 2D sonar with the depth perception typically associated with 3D systems. We have further incorporated Control Barrier Function (CBF) as a filter to ensure safety of the AUV. The effectiveness of this algorithm was tested on a six degrees of freedom (DOF) rover in various simulation scenarios. The results demonstrate that the system successfully avoids obstacles and navigates toward predefined goals, showcasing its capability to manage complex underwater environments with precision. This paper highlights the potential of 2.5D sonar for improving AUV navigation and offers insights into future enhancements and applications of this technology in underwater autonomous systems. \url{https://github.com/AIRLabIISc/EROAS}, Comment: Submitted to ICRA 2025

Here, we examine the latest advances in glaucoma detection through Deep Learning (DL) algorithms using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). This study focuses on three aspects of DL-based glaucoma detection frameworks: input data modalities, processing strategies, and model architectures and applications. Moreover, we analyze trends in employing each aspect since the onset of DL in this field. Finally, we address current challenges and suggest future research directions.

Distribution of entanglement is an essential task in quantum information processing and the realization of quantum networks. In our work, we theoretically investigate the scenario where a central source prepares an N-partite entangled state and transmits each entangled subsystem to one of N receivers through noisy quantum channels. The receivers are then able to perform local operations assisted by unlimited classical communication to distill target entangled states from the noisy channel output. In this operational context, we define the EPR distribution capacity and the GHZ distribution capacity of a quantum channel as the largest rates at which Einstein-Podolsky-Rosen (EPR) states and Greenberger-Horne-Zeilinger (GHZ) states can be faithfully distributed through the channel, respectively. We establish lower and upper bounds on the EPR distribution capacity by connecting it with the task of assisted entanglement distillation. We also construct an explicit protocol consisting of a combination of a quantum communication code and a classical-post-processing-assisted entanglement generation code, which yields a simple achievable lower bound for generic channels. As applications of these results, we give an exact expression for the EPR distribution capacity over two erasure channels and bounds on the EPR distribution capacity over two generalized amplitude damping channels. We also bound the GHZ distribution capacity, which results in an exact characterization of the GHZ distribution capacity when the most noisy channel is a dephasing channel.

We study the challenge of predicting the time at which a competitor product, such as a novel high-capacity EV battery or a new car model, will be available to customers; as new information is obtained, this time-to-market estimate is revised. Our scenario is as follows: We assume that the product is under development at a Firm B, which is a competitor to Firm A; as they are in the same industry, Firm A has a relatively good understanding of the processes and steps required to produce the product. While Firm B tries to keep its activities hidden (think of stealth-mode for start-ups), Firm A is nevertheless able to gain periodic insights by observing what type of resources Firm B is using. We show how Firm A can build a model that predicts when Firm B will be ready to sell its product; the model leverages knowledge of the underlying processes and required resources to build a Parallel Discrete Simulation (PDES)-based process model that it then uses as a generative model to train a Hidden Markov Model (HMM). We study the question of how many resource observations Firm A requires in order to accurately assess the current state of development at Firm B. In order to gain general insights into the capabilities of this approach, we study the effect of different process graph densities, different densities of the resource-activity maps, etc., and also scaling properties as we increase the number resource counts. We find that in most cases, the HMM achieves a prediction accuracy of 70 to 80 percent after 20 (daily) observations of a production process that lasts 150 days on average and we characterize the effects of different problem instance densities on this prediction accuracy. Our results give insight into the level of market knowledge required for accurate and early time-to-market prediction.

Self-dual Yang-Mills and Einstein gravity in Euclidean AdS$_4$ are useful toy models because they can be described by simple scalar Lagrangians exhibiting a new manifestation of the colour/kinematics duality, as recently shown by two of the authors. In this paper, we clarify how the self-dual sectors fit into the full theories. In particular, we explicitly construct the light-cone action for Yang-Mills theory and Einstein gravity in AdS$_4$ in terms of positive and negative helicity fields, where we are able to pinpoint the self-dual sector as expected. We then show that the boundary correlators of these theories take a remarkably simple form in terms of Feynman diagrams in half of flat space, acted on by certain differential operators. We also analyse their soft limits and show that they exhibit Weinberg-like soft factors, where the soft pole which appears in scattering amplitudes is replaced by a derivative with respect to the energy., Comment: 40 pages + 17 pages of appendix

Leakage, the occupation of any state not used in the computation, is one of the of the most devastating errors in quantum error correction. Transmons, the most common superconducting qubits, are weakly anharmonic multilevel systems, and are thus prone to this type of error. Here we demonstrate a device which reduces the lifetimes of the leakage states in the transmon by three orders of magnitude, while protecting the qubit lifetime and the single-qubit gate fidelties. To do this we attach a qubit through an on-chip seventh-order Chebyshev filter to a cold resistor. The filter is engineered such that the leakage transitions are in its passband, while the qubit transition is in its stopband. Dissipation through the filter reduces the lifetime of the transmon's $f$ state, the lowest energy leakage state, by three orders of magnitude to 33 ns, while simultaneously keeping the qubit lifetime to greater than 100 $\mu$s. Even though the $f$ state is transiently populated during a single qubit gate, no negative effect of the filter is detected with errors per gate approaching 1e-4. Modelling the filter as coupled linear harmonic oscillators, our theoretical analysis of the device corroborate our experimental findings. This leakage reduction unit turns leakage errors into errors within the qubit subspace that are correctable with traditional quantum error correction. We demonstrate the operation of the filter as leakage reduction unit in a mock-up of a single-qubit quantum error correcting cycle, showing that the filter increases the seepage rate back to the qubit subspace., Comment: 14 pages, 9 figures

Optical sensing technologies are emerging technologies used in cancer surgeries to ensure the complete removal of cancerous tissue. While point-wise assessment has many potential applications, incorporating automated large area scanning would enable holistic tissue sampling. However, such scanning tasks are challenging due to their long-horizon dependency and the requirement for fine-grained motion. To address these issues, we introduce Memorized Action Chunking with Transformers (MACT), an intuitive yet efficient imitation learning method for tissue surface scanning tasks. It utilizes a sequence of past images as historical information to predict near-future action sequences. In addition, hybrid temporal-spatial positional embeddings were employed to facilitate learning. In various simulation settings, MACT demonstrated significant improvements in contour scanning and area scanning over the baseline model. In real-world testing, with only 50 demonstration trajectories, MACT surpassed the baseline model by achieving a 60-80% success rate on all scanning tasks. Our findings suggest that MACT is a promising model for adaptive scanning in surgical settings.

We live in a world full of networks where our economy, our communication, and even our social life crucially depends on them. These networks typically emerge from the interaction of many entities, which is why researchers study agent-based models of network formation. While traditionally static networks with a fixed set of links were considered, a recent stream of works focuses on networks whose behavior may change over time. In particular, Bil\`o et al. (IJCAI 2023) recently introduced a game-theoretic network formation model that embeds temporal aspects in networks. More precisely, a network is formed by selfish agents corresponding to nodes in a given host network with edges having labels denoting their availability over time. Each agent strategically selects local, i.e., incident, edges to ensure temporal reachability towards everyone at low cost. In this work we set out to explore the impact of two novel conceptual features: agents are no longer restricted to creating incident edges, called the global setting, and agents might only want to ensure that they can reach a subset of the other nodes, called the terminal model. For both, we study the existence, structure, and quality of equilibrium networks. For the terminal model, we prove that many core properties crucially depend on the number of terminals. We also develop a novel tool that allows translating equilibrium constructions from the non-terminal model to the terminal model. For the global setting, we show the surprising result that equilibria in the global and the local model are incomparable and we establish a high lower bound on the Price of Anarchy of the global setting that matches the upper bound of the local model. This shows the counter-intuitive fact that allowing agents more flexibility in edge creation does not improve the quality of equilibrium networks.

Face recognition systems extract embedding vectors from face images and use these embeddings to verify or identify individuals. Face reconstruction attack (also known as template inversion) refers to reconstructing face images from face embeddings and using the reconstructed face image to enter a face recognition system. In this paper, we propose to use a face foundation model to reconstruct face images from the embeddings of a blackbox face recognition model. The foundation model is trained with 42M images to generate face images from the facial embeddings of a fixed face recognition model. We propose to use an adapter to translate target embeddings into the embedding space of the foundation model. The generated images are evaluated on different face recognition models and different datasets, demonstrating the effectiveness of our method to translate embeddings of different face recognition models. We also evaluate the transferability of reconstructed face images when attacking different face recognition models. Our experimental results show that our reconstructed face images outperform previous reconstruction attacks against face recognition models.

We show that a surjective homomorphism $\varphi \colon \Gamma \to K$ of (discrete) groups induces an isomorphism $H^\bullet_b(K; V) \to H^\bullet_b(\Gamma; \varphi^{-1} V)$ in bounded cohomology for all dual normed $K$-modules $V$ if and only if the kernel of $\varphi$ is boundedly acyclic. This complements a previous result by the authors that characterized this class of group homomorphisms as bounded cohomology equivalences with respect to $\mathbb{R}$-generated Banach $K$-modules. We deduce a characterization of the class of maps between path-connected spaces that induce isomorphisms in bounded cohomology with respect to coefficients in all dual normed modules, complementing the corresponding result shown previously in terms of $\mathbb{R}$-generated Banach modules. The main new input is the proof of the fact that every boundedly acyclic group $\Gamma$ has trivial bounded cohomology with respect to all dual normed trivial $\Gamma$-modules., Comment: 6 pages. To appear in Rev. Mat. Iberoam

Generative Artificial Intelligence (AI) technologies are in a phase of unprecedented rapid development following the landmark release of Chat-GPT, which brought the phenomenon to wide public attention. As the deployment of AI products rises geometrically, considerable attention is being given to the threats and opportunities that AI technologies offer, and to the need for regulatory and standards initiatives to ensure that use of the technology aligns with societal needs and generates broad benefits while mitigating risks and threats. This manuscript is the third of a series of White Papers informing the development of IEEE-SA's p3995 {\it `Standard for the Implementation of Safeguards, Controls, and Preventive Techniques for Artificial Intelligence Models'} \cite{P3395}, Chair Marina Cort\^{e}s. This part focuses on assessing calmly and objectively, as far as is possible, the current state of Artificial Intelligence (AI) technology development and identifying predominant trends, prospects, and ensuing risks. It necessarily forms a snapshot of the current instant of a rapidly-evolving landscape, with new products and innovations emerging continuously. While our main focus is on software and hardware developments and their corporate context, we also briefly review progress on robotics within the AI context and describe some implications of the substantial and growing AI energy demand., Comment: This is an interim version of our p3395 WG White Paper, Part III. We will update this version, until publication by IEEE-SA, Sponsor Committee - Artificial Intelligence Standards Committee (C/AISC); https://standards.ieee.org/ieee/3395/11378/ This White Paper is companion to Part I available at arXiv:2410.01808

We propose an object-centric recovery policy framework to address the challenges of out-of-distribution (OOD) scenarios in visuomotor policy learning. Previous behavior cloning (BC) methods rely heavily on a large amount of labeled data coverage, failing in unfamiliar spatial states. Without relying on extra data collection, our approach learns a recovery policy constructed by an inverse policy inferred from object keypoint manifold gradient in the original training data. The recovery policy serves as a simple add-on to any base visuomotor BC policy, agnostic to a specific method, guiding the system back towards the training distribution to ensure task success even in OOD situations. We demonstrate the effectiveness of our object-centric framework in both simulation and real robot experiments, achieving an improvement of 77.7% over the base policy in OOD. Project Website: https://sites.google.com/view/ocr-penn, Comment: Accepted for Spotlight (5 out of 21 papers) at CoRL 2024 Workshop on Lifelong Learning for Home Robots

ERSFQ circuits eliminate the dominant portion of static power consumption in RSFQ circuits by using current-limiting Josephson junctions and inductors instead of bias resistors. In practice, these junctions still contribute to static power consumption through switching required to correct phase imbalances across the circuit, with their contributions sometimes comparable to dynamic power. This paper presents a new SFQ family variant, called xeSFQ, that combines the clock-free alternating SFQ logic with ERSFQ's biasing. By ensuring a single pulse per line per logical cycle, xeSFQ eliminates even the residual switching due to phase imbalance, achieving truly zero static power consumption. Detailed analog simulations and synthesis results for various circuits, from single gates to ISCAS85 and EPFL benchmarks, validate the above hypothesis and showcase the all-around benefits of the proposed approach.

We revisit the phenomenology of dark-matter (DM) scenarios within radius-stabilized Randall-Sundrum models. Specifically, we consider models where the dark matter candidates are Standard Model (SM) singlets confined to the TeV brane and interact with the SM via spin-2 and spin-0 gravitational Kaluza-Klein (KK) modes. We compute the thermal relic density of DM particles in these models by applying recent work showing that scattering amplitudes of massive spin-2 KK states involve an intricate cancellation between various diagrams. Considering the resulting DM abundance, collider searches, and the absence of a signal in direct DM detection experiments, we show that spin-2 KK portal DM models are highly constrained. We confirm that within the usual thermal freeze-out scenario, scalar dark matter models are essentially ruled out. In contrast, we show that fermion and vector dark matter models are viable in a region of parameter space in which dark matter annihilation through a KK graviton is resonant. Specifically, vector models are viable for dark matter masses ranging from 1.1 TeV to 5.5 TeV for theories in which the scale of couplings of the KK modes is of order 40 TeV or lower. Fermion dark matter models are viable for a similar mass region, but only for KK coupling scales of order 20 TeV. In this work, we provide a complete description of the calculations needed to arrive at these results and, in an appendix, a discussion of new KK-graviton couplings needed for the computations, which have not previously been discussed in the literature. Here, we focus on models in which the radion is light, and the back-reaction of the radion stabilization dynamics on the gravitational background can be neglected. The phenomenology of a model with a heavy radion and the consideration of the effects of the radion stabilization dynamics on the DM abundance are being addressed in forthcoming work., Comment: 42 pages, 24 figures, We dedicate this work to the memory of Rohini Godbole (1952-2024) role model, mentor, and friend

The instruments at the focus of the Euclid space observatory offer superb, diffraction-limited imaging over an unprecedented (from space) wide field of view of 0.57 deg$^2$. This exquisite image quality has the potential to produce high-precision astrometry for point sources once the undersampling of Euclid's cameras is taken into account by means of accurate, effective point spread function (ePSF) modelling. We present a complex, detailed workflow to simultaneously solve for the geometric distortion (GD) and model the undersampled ePSFs of the Euclid detectors. Our procedure was successfully developed and tested with data from the Early Release Observations (ERO) programme focused on the nearby globular cluster NGC 6397. Our final one-dimensional astrometric precision for a well-measured star just below saturation is 0.7 mas (0.007 pixel) for the Visible Instrument (VIS) and 3 mas (0.01 pixel) for the Near-Infrared Spectrometer and Photometer (NISP). Finally, we present a specific scientific application of this high-precision astrometry: the combination of Euclid and Gaia data to compute proper motions and study the internal kinematics of NGC 6397. Future work, when more data become available, will allow for a better characterisation of the ePSFs and GD corrections that are derived here, along with assessment of their temporal stability, and their dependencies on the spectral energy distribution of the sources as seen through the wide-band filters of Euclid., Comment: 23 pages, 21 figures. Accepted for publication in A&A on October 24, 2024. Astro-photometric catalogs and stacked images will be available at the CDS after the paper will be published

In Industry 4.0 systems, a considerable number of resource-constrained Industrial Internet of Things (IIoT) devices engage in frequent data interactions due to the necessity for model training, which gives rise to concerns pertaining to security and privacy. In order to address these challenges, this paper considers a digital twin (DT) and blockchain-assisted federated learning (FL) scheme. To facilitate the FL process, we initially employ fog devices with abundant computational capabilities to generate DT for resource-constrained edge devices, thereby aiding them in local training. Subsequently, we formulate an FL delay minimization problem for FL, which considers both of model transmission time and synchronization time, also incorporates cooperative jamming to ensure secure synchronization of DT. To address this non-convex optimization problem, we propose a decomposition algorithm. In particular, we introduce upper limits on the local device training delay and the effects of aggregation jamming as auxiliary variables, thereby transforming the problem into a convex optimization problem that can be decomposed for independent solution. Finally, a blockchain verification mechanism is employed to guarantee the integrity of the model uploading throughout the FL process and the identities of the participants. The final global model is obtained from the verified local and global models within the blockchain through the application of deep learning techniques. The efficacy of our proposed cooperative interference-based FL process has been verified through numerical analysis, which demonstrates that the integrated DT blockchain-assisted FL scheme significantly outperforms the benchmark schemes in terms of execution time, block optimization, and accuracy.

The accuracy of face recognition systems has improved significantly in the past few years, thanks to the large amount of data collected and the advancement in neural network architectures. However, these large-scale datasets are often collected without explicit consent, raising ethical and privacy concerns. To address this, there have been proposals to use synthetic datasets for training face recognition models. Yet, such models still rely on real data to train the generative models and generally exhibit inferior performance compared to those trained on real datasets. One of these datasets, DigiFace, uses a graphics pipeline to generate different identities and different intra-class variations without using real data in training the models. However, the performance of this approach is poor on face recognition benchmarks, possibly due to the lack of realism in the images generated from the graphics pipeline. In this work, we introduce a novel framework for realism transfer aimed at enhancing the realism of synthetically generated face images. Our method leverages the large-scale face foundation model, and we adapt the pipeline for realism enhancement. By integrating the controllable aspects of the graphics pipeline with our realism enhancement technique, we generate a large amount of realistic variations-combining the advantages of both approaches. Our empirical evaluations demonstrate that models trained using our enhanced dataset significantly improve the performance of face recognition systems over the baseline. The source code and datasets will be made available publicly: https://www.idiap.ch/paper/digi2real, Comment: The dataset would be available here: https://www.idiap.ch/paper/digi2real

Core ellipticals, massive early-type galaxies have an almost constant inner surface brightness profile. The size of the core region correlates with the mass of the finally merged black hole. Here we report the first Euclid-based dynamical mass determination of a supermassive black hole. We study the centre of NGC 1272, the second most luminous elliptical galaxy in the Perseus cluster, combining the Euclid VIS photometry coming from the Early Release Observations of the Perseus cluster with VIRUS spectroscopic observations at the Hobby-Eberly Telescope. The core of NGC 1272 is detected on the Euclid VIS image. Its size is $1.29\pm 0.07''$ or 0.45 kpc, determined by fitting PSF-convolved core-S\'ersic and Nuker-law functions. The two-dimensional stellar kinematics of the galaxy is measured from the VIRUS spectra by deriving optimally regularized non-parametric line-of-sight velocity distributions. Dynamical models of the galaxy are constructed using our axisymmetric and triaxial Schwarzschild codes. We measure a black hole mass of $(5\pm3) \times 10^9 M_\odot$, in line with the expectation from the $M_{\rm BH}$-$r_{\rm b}$ correlation, but eight times larger than predicted by the $M_{\rm BH}$-$\sigma$ correlation (at $1.8\sigma$ significance). The core size, rather than the velocity dispersion, allows one to select galaxies harboring the most massive black holes. The spatial resolution, wide area coverage, and depth of the \Euclid (Wide and Deep) surveys allow us to find cores of passive galaxies larger than 2 kpc up to redshift 1., Comment: Accepted for publication in A&A

Here we show a photonic computing accelerator utilizing a system-level thin-film lithium niobate circuit which overcomes this limitation. Leveraging the strong electro-optic (Pockels) effect and the scalability of this platform, we demonstrate photonic computation at speeds up to 1.36 TOPS while consuming 0.057 pJ/OP. Our system features more than 100 thin-film lithium niobate high-performance components working synergistically, surpassing state-of-the-art systems on this platform. We further demonstrate binary-classification, handwritten-digit classification, and image classification with remarkable accuracy, showcasing our system's capability of executing real algorithms. Finally, we investigate the opportunities offered by combining our system with a hybrid-integrated distributed feedback laser source and a heterogeneous-integrated modified uni-traveling carrier photodiode. Our results illustrate the promise of thin-film lithium niobate as a computational platform, addressing current bottlenecks in both electronic and photonic computation. Its unique properties of high-performance electro-optic weight encoding and conversion, wafer-scale scalability, and compatibility with integrated lasers and detectors, position thin-film lithium niobate photonics as a valuable complement to silicon photonics, with extensions to applications in ultrafast and power-efficient signal processing and ranging.

Large language models (LLMs) excel in tasks requiring processing and interpretation of input text. Abstract screening is a labour-intensive component of systematic review involving repetitive application of inclusion and exclusion criteria on a large volume of studies identified by a literature search. Here, LLMs (GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, Llama 3 70B, Gemini 1.5 Pro, and Claude Sonnet 3.5) were trialled on systematic reviews in a full issue of the Cochrane Library to evaluate their accuracy in zero-shot binary classification for abstract screening. Trials over a subset of 800 records identified optimal prompting strategies and demonstrated superior performance of LLMs to human researchers in terms of sensitivity (LLM-max = 1.000, human-max = 0.775), precision (LLM-max = 0.927, human-max = 0.911), and balanced accuracy (LLM-max = 0.904, human-max = 0.865). The best performing LLM-prompt combinations were trialled across every replicated search result (n = 119,691), and exhibited consistent sensitivity (range 0.756-1.000) but diminished precision (range 0.004-0.096). 66 LLM-human and LLM-LLM ensembles exhibited perfect sensitivity with a maximal precision of 0.458, with less observed performance drop in larger trials. Significant variation in performance was observed between reviews, highlighting the importance of domain-specific validation before deployment. LLMs may reduce the human labour cost of systematic review with maintained or improved accuracy and sensitivity. Systematic review is the foundation of evidence synthesis across academic disciplines, including evidence-based medicine, and LLMs may increase the efficiency and quality of this mode of research., Comment: RS and AJT are joint-first authors