May 2024 arXiv papers — page 73

Lingxi Xiao, Muqing Li, Yinqiu Feng, Meiqi Wang

The research explores the utilization of a deep learning model employing an attention mechanism in medical text mining. It targets the challenge of analyzing unstructured text information within medical data. This research seeks to enhance the model's capability to identify essential medical information by incorporating deep learning and attention mechanisms

Shinji Mukohyama, Shinji Tsujikawa, Anzhong Wang

In Einstein-Aether gravity, we revisit the issue of linear stabilities of black holes against odd-parity perturbations on a static and spherically symmetric background. In this theory, superluminal propagation is allowed and there is a preferred timelike direction along the unit Aether vector field. If we choose the usual spherically symmetric background coo

Devlin Mallory

Let $X$ be a smooth variety over a field of characteristic $p$. It is a natural question whether the Frobenius pushforwards $F_*^e\mathcal O_X$ of the structure sheaf are tilting bundles. We show if $X$ is a smooth del Pezzo surface of degree $\leq 3$ or a Fano threefold with $\mathrm{vol}(K_X)<24$ over a field of characteristic $p$, then $\mathrm{Ext}^i(F_*

Alexander N. Pechen, Vadim N. Petruhanov, Oleg V. Morzhin, Boris O. Volkov

High fidelity generation of two-qubit gates is important for quantum computation, since such gates are components of popular universal sets of gates. Here we consider the problem of high fidelity generation of two-qubit C-NOT and C-PHASE (with a detailed study of C-Z) gates in presence of the environment. We consider the general situation when qubits are man

Alex Elzenaar, Shayne Waldron

We give some new explicit examples of putatively optimal projective spherical designs. i.e., ones for which there is numerical evidence that they are of minimal size. These form continuous families, and so have little apparent symmetry in general, which requires the introduction of new techniques for their construction. New examples of interest include an 11

Simon Neves, Adimulya Kartiyasa, Shayantani Ghosh, Geoffrey Gaulier

In recent years, quantum Fourier transform infrared (QFTIR) spectroscopy emerged as an alternative to conventional spectroscopy in the mid-infrared region of the spectrum. By harnessing induced coherence and spectral entanglement, QFTIR offers promising potential for the practical detection of organic gasses. However, little research was conducted to bring Q

Elie Bretin, Chih-Kang Huang, Simon Masnou

This paper addresses the approximation of the mean curvature flow of thin structures for which classical phase field methods are not suitable. By thin structures, we mean surfaces that are not domain boundaries, typically higher codimension objects such as 1D curves in 3D, i.e. filaments, or soap films spanning a boundary curve. To approximate the mean curva

Izzet Coskun, Jack Huizenga

In this paper, we study certain moduli spaces of vector bundles on the blowup of the projective plane in at least 10 very general points. Moduli spaces of sheaves on general type surfaces may be nonreduced, reducible and even disconnected. In contrast, moduli spaces of sheaves on minimal rational surfaces and certain del Pezzo surfaces are irreducible and sm

Nimish A. Shah, Pengyu Yang

For the space of unimodular lattices in a Euclidean space, we give necessary and sufficient conditions for equidistribution of expanding translates of any real-analytic submanifold under a diagonal flow. This extends the earlier result of Shah in the case of non-degenerate submanifolds. We apply the above dynamical result to show that if the affine span of a

Noah Bertram, Tean Lai, Justin Hsu

Envy-free cake-cutting protocols procedurally divide an infinitely divisible good among a set of agents so that no agent prefers another's allocation to their own. These protocols are highly complex and difficult to prove correct. Recently, Bertram, Levinson, and Hsu introduced a language called Slice for describing and verifying cake-cutting protocols. Slic

Eduardo da C. Ramos, Maria Luiza M. Campos, Fernanda Baião

Organizational decision-making is crucial for success, yet cognitive biases can significantly affect risk preferences, leading to suboptimal outcomes. Risk seeking preferences for losses, driven by biases such as loss aversion, pose challenges and can result in severe negative consequences, including financial losses. This research introduces the ABI approac

Vinod Raman, Ambuj Tewari

We study online classification when the learner has access to predictions about future examples. We design an online learner whose expected regret is never worse than the worst-case regret, gracefully improves with the quality of the predictions, and can be significantly better than the worst-case regret when the predictions of future examples are accurate.

Armando N. Perri, Laura K. McKemmish

Imidogen (NH) is a reactive molecule whose presence in astrochemical environments is of interest due to its role in the formation of nitrogen-containing molecules and as a potential probe of nitrogen abundance. Spectroscopic NH monitoring is useful for Earth-based combustion and photolysis processes of ammonia and other nitrogen-containing species. NH is als

Yinqiu Feng, Bo Zhang, Lingxi Xiao, Yutian Yang

In this research, we introduce an innovative method for synthesizing medical images using generative adversarial networks (GANs). Our proposed GANs method demonstrates the capability to produce realistic synthetic images even when trained on a limited quantity of real medical image data, showcasing commendable generalization prowess. To achieve this, we devi

Jake A. Soloff, Rina Foygel Barber, Rebecca Willett

We propose a new framework for algorithmic stability in the context of multiclass classification. In practice, classification algorithms often operate by first assigning a continuous score (for instance, an estimated probability) to each possible label, then taking the maximizer -- i.e., selecting the class that has the highest score. A drawback of this type

Dmitrii Zakharov

We show that if $A$ is a set of mutually orthogonal exponentials with respect to the unit disk then $|A \cap [-R, R]^2| \lesssim_\varepsilon R^{3/5+\varepsilon}$ holds. This improves the previous bound of $R^{2/3}$ by Iosevich--Kolountzakis. The main new ingredient in the proof is a discretized version of Marstrand's slicing theorem.

Jiawei Zhang, Chejian Xu, Bo Li

We present ChatScene, a Large Language Model (LLM)-based agent that leverages the capabilities of LLMs to generate safety-critical scenarios for autonomous vehicles. Given unstructured language instructions, the agent first generates textually described traffic scenarios using LLMs. These scenario descriptions are subsequently broken down into several sub-de

Tian Yu Liu, Stefano Soatto, Matteo Marchi, Pratik Chaudhari

We tackle the question of whether Large Language Models (LLMs), viewed as dynamical systems with state evolving in the embedding space of symbolic tokens, are observable. That is, whether there exist multiple 'mental' state trajectories that yield the same sequence of generated tokens, or sequences that belong to the same Nerode equivalence class ('meaning')

Martin Roa-Villescas, Xuanzhao Gao, Sander Stuijk, Henk Corporaal

Probabilistic inference is a fundamental task in modern machine learning. Recent advances in tensor network (TN) contraction algorithms have enabled the development of better exact inference methods. However, many common inference tasks in probabilistic graphical models (PGMs) still lack corresponding TN-based adaptations. In this work, we advance the connec

Xiaoyi Liu, Hongjie Qiu, Muqing Li, Zhou Yu

This paper introduces an innovative multi-modal fusion deep learning approach to overcome the drawbacks of traditional single-modal recognition techniques. These drawbacks include incomplete information and limited diagnostic accuracy. During the feature extraction stage, cutting-edge deep learning models including convolutional neural networks (CNN), recurr

Brandon Legried

Non-coding RNA are functional molecules that are not translated into proteins. Their function comes as important regulators of biological function. Because they are not translated, they need not be as stable as other types of RNA. The TKF91 Structure Tree from Holmes 2004 is a probability model that effectively describes correlated substitution, insertion, a

Steven Carlip

Causal set theory offers a simple and elegant picture of discrete physics. But the vast majority of causal sets look nothing at all like continuum spacetimes, and must be excluded in some way to obtain a realistic theory. I describe recent results showing that almost all non-manifoldlike causal sets are, in fact, very strongly suppressed in the gravitational

Udayan Mandal, Guy Amir, Haoze Wu, Ieva Daukantas

Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating agents that control autonomous systems. However, the ``black box'' nature of DRL agents limits their deployment in real-world safety-critical applications. A promising approach for providing strong guarantees on an agent's behavior is to use Neural Lyapunov Barrier (NLB)

Hope McGovern, Rickard Stureborg, Yoshi Suhara, Dimitris Alikaniotis

It has been shown that finetuned transformers and other supervised detectors effectively distinguish between human and machine-generated text in some situations arXiv:2305.13242, but we find that even simple classifiers on top of n-gram and part-of-speech features can achieve very robust performance on both in- and out-of-domain data. To understand how this

Fabio Briscese, Gianluca Calcagni, Leonardo Modesto, Giuseppe Nardelli

We discuss the conical region of convergence of exponential and asymptotically polynomial form factors and their integral representations. Then, we calculate the spectral representation of the propagator of nonlocal theories with entire form factors, in particular, of the above type. The spectral density is positive-definite and exhibits the same spectrum as

Richard Antonello, Nihita Sarma, Jerry Tang, Jiaru Song

Brain-computer interfaces have promising medical and scientific applications for aiding speech and studying the brain. In this work, we propose an information-based evaluation metric for brain-to-text decoders. Using this metric, we examine two methods to augment existing state-of-the-art continuous text decoders. We show that these methods, in concert, can

Gil R. Cavalcanti, Bart Heemskerk, Bernardo Uribe

Topological Spherical T-duality was introduced by Bouwknegt, Evslin and Mathai in [BEM15] as an extension of topological T-duality from $S^1$-bundles to $\mathrm{SU}(2)$-bundles endowed with closed 7-forms. This notion was further extended to sphere bundles by Lind, Sati and Westerland [LSW16] as a duality between $S^{2n-1}$-bundles endowed with closed $(4n-

Henri Alam, Antonio de Domenico, Florian Kaltenberger, David López-Pérez

Due to an ever-expansive network deployment, numerous questions are being raised regarding the energy consumption of the mobile network. Recently, Non-Terrestrial Networks (NTNs) have proven to be a useful, and complementary solution to Terrestrial Networks (TN) to provide ubiquitous coverage. In this paper, we consider an integrated TN-NTN, and study how to

Seshagiri Prabhu Narasimha, Arun Lakhotia

Knowledge of the input format of binary executables is important for finding bugs and vulnerabilities, such as generating data for fuzzing or manual reverse engineering. This paper presents an algorithm to recover the structure and semantic relations between fields of the input of binary executables using dynamic taint analysis. The algorithm improves upon p

Yijin Ni, Xiaoming Huo

In many contemporary statistical and machine learning methods, one needs to optimize an objective function that depends on the discrepancy between two probability distributions. The discrepancy can be referred to as a metric for distributions. Widely adopted examples of such a metric include Energy Distance (ED), distance Covariance (dCov), Maximum Mean Disc

Yang Hu, Dennis M. Kochmann, Brandon Runnels

The nucleation and propagation of disconnections play an essential role during twin growth. Atomistic methods can reveal such small structural features on twin facets and model their motion, yet are limited by the simulation length and time scales. Alternatively, mesoscale modeling approaches (such as the phase field method) address these constraints of atom

Karol Rogoziński, Jan Dubiński, Przemysław Rokita, Kamil Deja

The research of innovative methods aimed at reducing costs and shortening the time needed for simulation, going beyond conventional approaches based on Monte Carlo methods, has been sparked by the development of collision simulations at the Large Hadron Collider at CERN. Deep learning generative methods including VAE, GANs and diffusion models have been used

Silvia Novo, Germán Aneiros

Functional data analysis has become a tool of interest in applied areas such as economics, medicine, and chemistry. Among the techniques developed in recent literature, functional semiparametric regression stands out for its balance between flexible modelling and output interpretation. Despite the large variety of research papers dealing with scalar-on-funct

Adesunmbo Adeboye Adeagbo

In this project a modern approach and technology are adopted for monitoring the environmental conditions in a particular location. This system is efficient in retrieving the environmental data from the device because the environmental conditions change spontaneously based on different atmospheric conditions. There is a need for us to pay close attention to o

S. Zargari, D. Galappaththige, C. Tellambura

Bistatic backscatter communication facilitates ubiquitous, massive connectivity of passive tags for future Internet-of-Things (IoT) networks. The tags communicate with readers by reflecting carrier emitter (CE) signals. This work addresses the joint design of the transmit/receive beamformers at the CE/reader and the reflection coefficient of the tag. A throu

Yulia Rubanova, Tatiana Lopez-Guevara, Kelsey R. Allen, William F. Whitney

Simulating large scenes with many rigid objects is crucial for a variety of applications, such as robotics, engineering, film and video games. Rigid interactions are notoriously hard to model: small changes to the initial state or the simulation parameters can lead to large changes in the final state. Recently, learned simulators based on graph networks (GNN

Ibrahim Isik, Mitra Rezaei, Adam Noel

Spheroids are aggregates of cells that can mimic the cellular organization often found in tissues. They are typically formed through the self-assembly of cells in a culture where there is a promotion of interactions and cell-to-cell communication. Spheroids can be created from various cell types, including cancer cells, stem cells, and primary cells, and the

Yerka Freire-Vidal, Gabriela Fajardo, Carlos Rodríguez-Sickert, Eduardo Graells-Garrido

The COVID-19 outbreak implied many changes in the daily life of most of the world's population for a long time, prompting severe restrictions on sociality. The Behavioral Immune System (BIS) suggests that when facing pathogens, a psychological mechanism would be activated that, among other things, would generate an increase in prejudice and discrimination to

Ricardo Loor-Torres, Yuqi Wu, Esteban Cabezas, Mariana Borras

Background We aim to use Natural Language Processing (NLP) to automate the extraction and classification of thyroid cancer risk factors from pathology reports. Methods We analyzed 1,410 surgical pathology reports from adult papillary thyroid cancer patients at Mayo Clinic, Rochester, MN, from 2010 to 2019. Structured and non-structured reports were used to c

Abel Castorena, Frank Neumann

We study the various arithmetic and geometric Frobenius morphisms on the moduli stack of principal bundles over a smooth projective algebraic curve and determine explicitly their actions on the $\ell-$adic cohomology of the moduli stack in terms of Chern classes.

Alexander Burstein, Tian Han, Sergey Kitaev, Philip Zhang

We prove a conjecture of Gao and Kitaev on Wilf-equivalence of sets of patterns {12345,12354} and {45123,45213} that extends the list of 10 related conjectures proved in the literature in a series of papers. To achieve our goals, we prove generalized versions of shape-Wilf-equivalence results of Backelin, West, and Xin and use a particular result on shape-Wi

Dingyi Yang, Chunru Zhan, Ziheng Wang, Biao Wang

Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video captioning and video story generation have made some progress. However, in practical applications, we typically require synchroni

Yiming Wang, Pei Zhang, Baosong Yang, Derek F. Wong

Real-world data deviating from the independent and identically distributed (i.i.d.) assumption of in-distribution training data poses security threats to deep networks, thus advancing out-of-distribution (OOD) detection algorithms. Detection methods in generative language models (GLMs) mainly focus on uncertainty estimation and embedding distance measurement

Sunrit Chakraborty, Saptarshi Roy, Debabrota Basu

High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems (e.g. personalized medicine), where high dimensional features (e.g. genomic data) on the users are available, but only a small subset of them are relevant. Motivated by data privacy concerns in these applications, we study the joint differentially priva

Abel Castorena, Frank Neumann

We study moduli stacks of principal $\Bbb C^*$-bundles over nodal complex algebraic curves and determine their rational cohomology algebras in terms of Chern classes.

Zihao Su, Kunlin Cai, Reuben Beeler, Lukas Dresel

As Virtual Reality (VR) applications grow in popularity, they have bridged distances and brought users closer together. However, with this growth, there have been increasing concerns about security and privacy, especially related to the motion data used to create immersive experiences. In this study, we highlight a significant security threat in multi-user V

Shashank Gupta, Reza Moini

Cortical bone is a tough biological material composed of tube-like osteons embedded in the organic matrix surrounded by weak interfaces known as cement lines. The cement lines provide a microstructurally preferable crack path, hence triggering in-plane crack deflection around osteons due to cement line-crack interaction. Here, inspired by this toughening mec

Alice Li, Luanne Sinnamon

This paper reports on an audit study of generative AI systems (ChatGPT, Bing Chat, and Perplexity) which investigates how these new search engines construct responses and establish authority for topics of public importance. We collected system responses using a set of 48 authentic queries for 4 topics over a 7-day period and analyzed the data using sentiment

Daniel Kuelbs, Sanjay Lall, Mert Pilanci

Training neural networks which are robust to adversarial attacks remains an important problem in deep learning, especially as heavily overparameterized models are adopted in safety-critical settings. Drawing from recent work which reformulates the training problems for two-layer ReLU and polynomial activation networks as convex programs, we devise a convex s

Sungho Shin, Vishwas Rao, Michel Schanen, D. Adrian Maldonado

This paper demonstrates the scalability of open-source GPU-accelerated nonlinear programming (NLP) frameworks -- ExaModels.jl and MadNLP.jl -- for solving multi-period alternating current (AC) optimal power flow (OPF) problems on GPUs with high memory capacities (e.g., NVIDIA GH200 with 480 GB of unified memory). There has been a growing interest in solving

Eunhyek Joa, Eric Yongkeun Choi, Francesco Borrelli

This paper presents a data-driven Model Predictive Control (MPC) for energy-efficient urban road driving for connected, automated vehicles. The proposed MPC aims to minimize total energy consumption by controlling the vehicle's longitudinal motion on roads with traffic lights and front vehicles. Its terminal cost function and terminal constraints are learned

Haocheng Dai, Sarang Joshi

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems, inherit biases from the disproportionate distribution of real-world data, leading to misconceptions about the actual enviro

Yanjun Wu, Zhong Xie, Zhuochen Xie, Chongjun Ouyang

The average multicast rate (AMR) is analyzed in a multicast channel utilizing analog beamforming with finite-alphabet inputs, considering statistical channel state information (CSI). New expressions for the AMR are derived for non-cooperative and cooperative multicasting scenarios. Asymptotic analyses are conducted in the high signal-to-noise ratio regime to

Petros Liakopoulos, Julien Massonnet, Jonatan Bonjour, Medya Tekes Mizrakli

In computational digital pathology, accurate nuclear segmentation of Hematoxylin and Eosin (H&E) stained whole slide images (WSIs) is a critical step for many analyses and tissue characterizations. One popular deep learning-based nuclear segmentation approach, HoverNet, offers remarkably accurate results but lacks the high-throughput performance needed for c

Yujun Choi, John M. Nichol, Edwin Barnes

Semiconductor spin qubits are an attractive platform for quantum computing, but their performance is degraded primarily by fluctuating electromagnetic environments. We introduce the concept of ballast charges, which are induced charges on the surface of an additional screening layer situated below the qubits. The counteractive behavior of these charges can s

Wei-Yang Liu, Edward Shuryak, Christian Weiss, Ismail Zahed

The pion form factors of the QCD energy-momentum tensor (EMT) are studied in the instanton liquid model (ILM) of the QCD vacuum. In this approach the breaking of conformal symmetry is encoded in the form of stronger-than-Poisson fluctuations in the number of instantons. For the trace of the EMT, it is shown that the gluonic trace anomaly term contributes hal

Zilin Xu, Zahra Montazeri, Beibei Wang, Ling-Qi Yan

Measured Bidirectional Texture Function (BTF) can faithfully reproduce a realistic appearance but is costly to acquire and store due to its 6D nature (2D spatial and 4D angular). Therefore, it is practical and necessary for rendering to synthesize BTFs from a small example patch. While previous methods managed to produce plausible results, we find that they

Mykhailo Uss, Ruslan Yermolenko, Oleksii Shashko, Olena Kolodiazhna

Dense depth prediction deep neural networks (DNN) have achieved impressive results for both monocular and binocular data, but still they are limited by high computational complexity, restricting their use on low-end devices. For better on-device efficiency and hardware utilization, weights and activations of the DNN should be converted to low-bit precision.

Tianrong Zhang, Bochuan Cao, Yuanpu Cao, Lu Lin

The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to jailbreaking attacks, which leads to the generation of harmful or unsafe content. While safety alignment measures have been implemented in

Omer F. Atli, Bilal Kabas, Fuat Arslan, Arda C. Demirtas

Multi-modal medical image synthesis involves nonlinear transformation of tissue signals between source and target modalities, where tissues exhibit contextual interactions across diverse spatial distances. As such, the utility of a network architecture in synthesis depends on its ability to express the broad set of contextual features in medical images. Conv

Yangming Li, Yixin Cheng, Mihaela van der Schaar

Latent diffusion has demonstrated promising results in image generation and permits efficient sampling. However, this framework might suffer from the problem of posterior collapse when applied to time series. In this paper, we first show that posterior collapse will reduce latent diffusion to a variational autoencoder (VAE), making it less expressive. This h

Ling Han, Hao Huang, Dustin Scheinost, Mary-Anne Hartley

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional approaches typically assume that data variations are random, which makes it difficult to adjust the model parameters accurate

Alan Q. Wang, Rachit Saluja, Heejong Kim, Xinzi He

We present a keypoint-based foundation model for general purpose brain MRI registration, based on the recently-proposed KeyMorph framework. Our model, called BrainMorph, serves as a tool that supports multi-modal, pairwise, and scalable groupwise registration. BrainMorph is trained on a massive dataset of over 100,000 3D volumes, skull-stripped and non-skull

Hengzhi He, Peiyu Yu, Junpeng Ren, Ying Nian Wu

In this paper, we introduce a simple yet effective tabular data watermarking mechanism with statistical guarantees. We show theoretically that the proposed watermark can be effectively detected, while faithfully preserving the data fidelity, and also demonstrates appealing robustness against additive noise attack. The general idea is to achieve the watermark

Hao Zhang, Di Chang, Fang Li, Mohammad Soleymani

With the success of 2D and 3D visual generative models, there is growing interest in generating 4D content. Existing methods primarily rely on text prompts to produce 4D content, but they often fall short of accurately defining complex or rare motions. To address this limitation, we propose MagicPose4D, a novel framework for refined control over both appeara

Juan D. Pinto, Luc Paquette

The challenge of creating interpretable models has been taken up by two main research communities: ML researchers primarily focused on lower-level explainability methods that suit the needs of engineers, and HCI researchers who have more heavily emphasized user-centered approaches often based on participatory design methods. This paper reviews how these comm

Euclid Collaboration, K. Voggel, A. Lançon, T. Saifollahi

Extragalactic globular clusters (EGCs) are an abundant and powerful tracer of galaxy dynamics and formation, and their own formation and evolution is also a matter of extensive debate. The compact nature of globular clusters means that they are hard to spatially resolve and thus study outside the Local Group. In this work we have examined how well EGCs will

Fangqiang Ding, Xiangyu Wen, Yunzhou Zhu, Yiming Li

3D occupancy-based perception pipeline has significantly advanced autonomous driving by capturing detailed scene descriptions and demonstrating strong generalizability across various object categories and shapes. Current methods predominantly rely on LiDAR or camera inputs for 3D occupancy prediction. These methods are susceptible to adverse weather conditio

Kai Shinbrough, Donny R. Pearson, Virginia O. Lorenz, Elizabeth A. Goldschmidt

Photonic quantum memory is a crucial elementary operation in photonic quantum information processing. While many physically distinct memory protocols and hardware implementations have been applied to this task, the development of a quantum memory performant in all relevant metrics simultaneously (e.g., efficiency, bandwidth, lifetime, etc.) is still an open

Tolga Çöplü, Arto Bendiken, Andrii Skomorokhov, Eduard Bateiko

In applications such as personal assistants, large language models (LLMs) must consider the user's personal information and preferences. However, LLMs lack the inherent ability to learn from user interactions. This paper explores capturing personal information from user prompts using ontology and knowledge-graph approaches. We use a subset of the KNOW ontolo

Michalis Chatzittofi, Jaime Agudo-Canalejo, Ramin Golestanian

Chemical affinities are responsible for driving active matter systems out of equilibrium. At the nano-scale, molecular machines interact with the surrounding environment and are subjected to external forces. The mechano-chemical coupling which arises naturally in these systems reveals a complex interplay between chemical and mechanical degrees of freedom wit

Baiyu Chen, Sixian Chan, Xiaoqin Zhang

Video Object Segmentation (VOS) aims to track objects across frames in a video and segment them based on the initial annotated frame of the target objects. Previous VOS works typically rely on fully annotated videos for training. However, acquiring fully annotated training videos for VOS is labor-intensive and time-consuming. Meanwhile, self-supervised VOS m

Swapnil Gandhi, Mark Zhao, Athinagoras Skiadopoulos, Christos Kozyrakis

Training large Deep Neural Network (DNN) models requires thousands of GPUs over the course of several days or weeks. At this scale, failures are frequent and can have a big impact on training throughput. Utilizing spare GPU servers to mitigate performance loss becomes increasingly costly as model sizes grow. ReCycle is a system designed for efficient DNN tra

Qiuyi Chen, Panagiotis Tsilifis, Mark Fuge

Solving inverse problems in scientific and engineering fields has long been intriguing and holds great potential for many applications, yet most techniques still struggle to address issues such as high dimensionality, nonlinearity and model uncertainty inherent in these problems. Recently, generative models such as Generative Adversarial Networks (GANs) have

Yan Zhao, Amy Otteson

Enrollment projection is a critical aspect of university management, guiding decisions related to resource allocation and revenue forecasting. However, despite its importance, there remains a lack of transparency regarding the methodologies utilized by many institutions. This paper presents an innovative approach to enrollment projection using Markov Chain m

Birger Moell

In the rapidly evolving field of artificial intelligence, large language models (LLMs) have demonstrated significant capabilities across numerous applications. However, the performance of these models in languages with fewer resources, such as Swedish, remains under-explored. This study introduces a comprehensive human benchmark to assess the efficacy of pro

Sebastian Sartor, Neil Thompson

Neural scaling laws have driven significant advancements in machine learning, particularly in domains like language modeling and computer vision. However, the exploration of neural scaling laws within robotics has remained relatively underexplored, despite the growing adoption of foundation models in this field. This paper represents the first comprehensive

Srija Chakraborty

Artificial Intelligence, machine learning (AI/ML) has allowed exploring solutions for a variety of environmental and climate questions ranging from natural disasters, greenhouse gas emission, monitoring biodiversity, agriculture, to weather and climate modeling, enabling progress towards climate change mitigation. However, the intersection of AI/ML and envir

Washington F. dos Santos, Felippe Amorim, Alexandre Reily Rocha

Carbon-based nanostructures have unparalleled electronic properties. At the same time, using an allotrope of carbon as the contacts can yield better device control and reproducibility. In this work, we simulate a single-electron transistor composed of a segment of a graphene nanoribbon coupled to carbon nanotubes electrodes. Using the non-equilibrium Green's

Edoardo Fazzari, Donato Romano, Fabrizio Falchi, Cesare Stefanini

Animal behavior serves as a reliable indicator of the adaptation of organisms to their environment and their overall well-being. Through rigorous observation of animal actions and interactions, researchers and observers can glean valuable insights into diverse facets of their lives, encompassing health, social dynamics, ecological relationships, and neuroeth

Sander Beckers

I generalize acyclic deterministic structural causal models to the nondeterministic case and argue that this offers an improved semantics for counterfactuals. The standard, deterministic, semantics developed by Halpern (and based on the initial proposal of Galles & Pearl) assumes that for each assignment of values to parent variables there is a unique assign

Yifei Li, Yuchen Sun, Pingchuan Ma, Eftychios Sifakis

We present a novel framework to explore neural control and design of complex fluidic systems with dynamic solid boundaries. Our system features a fast differentiable Navier-Stokes solver with solid-fluid interface handling, a low-dimensional differentiable parametric geometry representation, a control-shape co-design algorithm, and gym-like simulation enviro

Michel Aguilera, Sergio Pino-Alarcón, Francisco J. Peña, Eugenio E. Vogel

In this work, we study the magnetocaloric effect (MCE) in a working substance corresponding to a square lattice of spins with $Q$ possible orientations, known as the ``$Q$-state clock model". When the $Q$-state clock model has $Q\geq 5$ possible configurations, it presents the famous Berezinskii Kosterlitz Thouless (BKT) phase associated with vortices states

Hari Iyer, Neel Macwan, Shenghan Guo, Heejin Jeong

The performance of physical workers is significantly influenced by the extent of their motions. However, monitoring and assessing these motions remains a challenge. Recent advancements have enabled in-situ video analysis for real-time observation of worker behaviors. This paper introduces a novel framework for tracking and quantifying upper and lower limb mo

Sifan Wang, Jacob H Seidman, Shyam Sankaran, Hanwen Wang

Operator learning, which aims to approximate maps between infinite-dimensional function spaces, is an important area in scientific machine learning with applications across various physical domains. Here we introduce the Continuous Vision Transformer (CViT), a novel neural operator architecture that leverages advances in computer vision to address challenges

Huy Nguyen, Nhat Ho, Alessandro Rinaldo

The softmax gating function is arguably the most popular choice in mixture of experts modeling. Despite its widespread use in practice, the softmax gating may lead to unnecessary competition among experts, potentially causing the undesirable phenomenon of representation collapse due to its inherent structure. In response, the sigmoid gating function has been

Yiwen Dong, Yuyan Wu, Hae Young Noh

Gait abnormality detection is critical for the early discovery and progressive tracking of musculoskeletal and neurological disorders, such as Parkinson's and Cerebral Palsy. Especially, analyzing the foot-floor contacts during walking provides important insights into gait patterns, such as contact area, contact force, and contact time, enabling gait abnorma

Dan Kalifa, Uriel Singer, Ido Guy, Guy D. Rosin

Consumer demand forecasting is of high importance for many e-commerce applications, including supply chain optimization, advertisement placement, and delivery speed optimization. However, reliable time series sales forecasting for e-commerce is difficult, especially during periods with many anomalies, as can often happen during pandemics, abnormal weather, o

Naibo Wang, Yuchen Deng, Wenjie Feng, Jianwei Yin

Federated Class Incremental Learning (FCIL) is a critical yet largely underexplored issue that deals with the dynamic incorporation of new classes within federated learning (FL). Existing methods often employ generative adversarial networks (GANs) to produce synthetic images to address privacy concerns in FL. However, GANs exhibit inherent instability and hi

Murad Tukan, Loay Mualem, Moran Feldman

Non-monotone constrained submodular maximization plays a crucial role in various machine learning applications. However, existing algorithms often struggle with a trade-off between approximation guarantees and practical efficiency. The current state-of-the-art is a recent $0.401$-approximation algorithm, but its computational complexity makes it highly impra

Chenying Liu, Hunsoo Song, Anamika Shreevastava, Conrad M Albrecht

Local climate zones (LCZs) established a standard classification system to categorize the landscape universe for improved urban climate studies. Existing LCZ mapping is guided by human interaction with geographic information systems (GIS) or modelled from remote sensing (RS) data. GIS-based methods do not scale to large areas. However, RS-based methods lever

Hongyu Cheng, Amitabh Basu

The branch-and-cut algorithm is the method of choice to solve large scale integer programming problems in practice. A key ingredient of branch-and-cut is the use of cutting planes which are derived constraints that reduce the search space for an optimal solution. Selecting effective cutting planes to produce small branch-and-cut trees is a critical challenge

Ruonan Wang, John W. Chew, Feng Gao, Olaf Marxen

Flow and heat transfer in a compressor rotating disc cavity with axial throughflow is investigated using wall-modelled large-eddy simulations (WMLES). These are compared to measurements from recently published experiments and used to investigate high Reynolds number effects. The simulations use an open-source CFD solver with high parallel efficiency and empl

Jerzy Szulga

We discuss the Gamma Levy process, including path properties, the inverse process, integrability, and its spin-offs obtained by compounding, exponentiation, and other operations; further extendable to arbitrary sigma-finite continuous Borel spaces. An appendix on modular spaces and deterministic jump processes is included.

Diogo Lavado, Cláudia Soares, Alessandra Micheletti, Ricardo Santos

Research on supervised learning algorithms in 3D scene understanding has risen in prominence and witness great increases in performance across several datasets. The leading force of this research is the problem of autonomous driving followed by indoor scene segmentation. However, openly available 3D data on these tasks mainly focuses on urban scenarios. In t

Johannes Lohmann, Valerio Lucarini

The Atlantic Meridional Overturning Circulation (AMOC) is a much studied component of the climate system, because its suspected multistability is associated with tipping behaviour yielding potentially large regional and global climatic impacts. In this paper we investigate the global stability properties of the system using an ocean general circulation model

Robert Wang, Aseem Baranwal, Kimon Fountoulakis

Machine learning for node classification on graphs is a prominent area driven by applications such as recommendation systems. State-of-the-art models often use multiple graph convolutions on the data, as empirical evidence suggests they can enhance performance. However, it has been shown empirically and theoretically, that too many graph convolutions can deg

Sanchayan Dutta, Xiang Cheng, Suvrit Sra

We develop new algorithms for Riemannian bilevel optimization. We focus in particular on batch and stochastic gradient-based methods, with the explicit goal of avoiding second-order information such as Riemannian hyper-gradients. We propose and analyze $\mathrm{RF^2SA}$, a method that leverages first-order gradient information to navigate the complex geometr

Armando Coco, Giovanni Russo

In this paper a fourth order finite difference ghost point method for the Poisson equation on regular Cartesian mesh is presented. The method can be considered the high order extension of the second ghost method introduced earlier by the authors. Three different discretizations are considered, which differ in the stencil that discretizes the Laplacian and th

Anthony Fuller, Daniel G. Kyrollos, Yousef Yassin, James R. Green

High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without finetuning -- ViTs poorly extrapolate to more patches at test time, although transformers offer sequence length flexibility. We