May 2024 arXiv papers — page 30

Yifan Bai, Dongming Wu, Yingfei Liu, Fan Jia

Rapid advancements in Autonomous Driving (AD) tasks turned a significant shift toward end-to-end fashion, particularly in the utilization of vision-language models (VLMs) that integrate robust logical reasoning and cognitive abilities to enable comprehensive end-to-end planning. However, these VLM-based approaches tend to integrate 2D vision tokenizers and a

Assaf Shani

Fix $n=1,2,3,\dots$ or $n=\omega$. We prove a dichotomy for Borel homomorphisms from the $n$-th Friedman-Stanley jump $=^{+n}$ to an equivalence relation $E$ which is classifiable by countable structures: if there is no reduction from $=^{+n}$ to $E$, then in fact all Borel homomorphisms are very far from a reduction. For this we use a different presentation

Somnath Kumar, Vaibhav Balloli, Mercy Ranjit, Kabir Ahuja

Large language models (LLMs) are at the forefront of transforming numerous domains globally. However, their inclusivity and effectiveness remain limited for non-Latin scripts and low-resource languages. This paper tackles the imperative challenge of enhancing the multilingual performance of LLMs without extensive training or fine-tuning. Through systematic i

Somnath Kumar, Yash Gadhia, Tanuja Ganu, Akshay Nambi

Recent advancements in Multi-modal Large Language Models (MLLMs) have significantly improved their performance in tasks combining vision and language. However, challenges persist in detailed multi-modal understanding, comprehension of complex tasks, and reasoning over multi-modal information. This paper introduces MMCTAgent, a novel multi-modal critical thin

Jundong Xu, Hao Fei, Liangming Pan, Qian Liu

While the recent Chain-of-Thought (CoT) technique enhances the reasoning ability of large language models (LLMs) with the theory of mind, it might still struggle in handling logical reasoning that relies much on symbolic expressions and rigid deducing rules. To strengthen the logical reasoning capability of LLMs, we propose a novel Symbolic Chain-of-Thought,

Jie Liu, Yixiao Zhang, Kang Wang, Mehmet Can Yavuz

The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often struggle with flexibility for partially annotated datasets and extensibility for new classes due to limitations in the one

Francesco De Dominicis, Tanay Roy, Ambra Mariani, Mustafa Bal

Superconducting qubits can be sensitive to abrupt energy deposits caused by cosmic rays and ambient radioactivity. While previous studies have explored correlated effects in time and space due to cosmic ray interactions, we present the first direct comparison of a transmon qubit's performance measured at two distinct sites: the above-ground SQMS facility (Fe

Matthew C. B. Zaremsky

Given a group $G$ acting faithfully on a set $S$, we characterize precisely when the twisted Brin-Thompson group $SV_G$ is finitely presented. The answer is that $SV_G$ is finitely presented if and only if we have the following: $G$ is finitely presented, the action of $G$ on $S$ has finitely many orbits of two-element subsets of $S$, and the stabilizer in $

Gefan Yang, Elizabeth Louise Baker, Michael L. Severinsen, Christy Anna Hipsley

The diffusion bridge, which is a diffusion process conditioned on hitting a specific state within a finite period, has found broad applications in various scientific and engineering fields. However, simulating diffusion bridges for modeling natural data can be challenging due to both the intractability of the drift term and continuous representations of the

Carlos Cotta, José E. Gallardo

The problem of finding the optimal placement of emergency exits in an indoor environment to facilitate the rapid and orderly evacuation of crowds is addressed in this work. A cellular-automaton model is used to simulate the behavior of pedestrians in such scenarios, taking into account factors such as the environment, the pedestrians themselves, and the inte

Devina Mohan, Anna M. M. Scaife

The radio astronomy community is rapidly adopting deep learning techniques to deal with the huge data volumes expected from the next generation of radio observatories. Bayesian neural networks (BNNs) provide a principled way to model uncertainty in the predictions made by such deep learning models and will play an important role in extracting well-calibrated

Anjanava Biswas

This paper presents a case study of how Petco, a leading pet retailer, innovated their pet health analysis processes using the Media Insights Engine to reduce the time to first diagnosis. The company leveraged this framework to build custom applications for advanced computer vision tasks, such as identifying potential health issues in pet videos and images,

Silvia García Méndez, Milagros Fernández Gavilanes, Enrique Costa Montenegro, Jonathan Juncal Martínez

We present an automatic text expansion system to generate English sentences, which performs automatic Natural Language Generation (NLG) by combining linguistic rules with statistical approaches. Here, "automatic" means that the system can generate coherent and correct sentences from a minimum set of words. From its inception, the design is modular and adapta

Andreas Ekstedt, Philipp Schicho, Tuomas V. I. Tenkanen

We complete the perturbative program for equilibrium thermodynamics of cosmological first-order phase transitions by determining the finite-temperature effective potential of gauge-Higgs theories at next-to-next-to-next-to-next-to-leading order (N$^4$LO). The computation of the three-loop effective potential required to reach this order is extended to generi

Sweta Agrawal, António Farinhas, Ricardo Rei, André F. T. Martins

Automatic metrics for evaluating translation quality are typically validated by measuring how well they correlate with human assessments. However, correlation methods tend to capture only the ability of metrics to differentiate between good and bad source-translation pairs, overlooking their reliability in distinguishing alternative translations for the same

Ziheng Qin, Zhaopan Xu, Yukun Zhou, Zangwei Zheng

Deep learning benefits from the growing abundance of available data. Meanwhile, efficiently dealing with the growing data scale has become a challenge. Data publicly available are from different sources with various qualities, and it is impractical to do manual cleaning against noise and redundancy given today's data scale. There are existing techniques for

Anjanava Biswas, Wrick Talukdar

Comprehensive clinical documentation is crucial for effective healthcare delivery, yet it poses a significant burden on healthcare professionals, leading to burnout, increased medical errors, and compromised patient safety. This paper explores the potential of generative AI (Artificial Intelligence) to streamline the clinical documentation process, specifica

Ivan Tambovtsev, Yorick L. A. Schmerwitz, Gianluca Levi, Darina D. Darmoroz

The relaxation time of several second generation molecular motors is analysed by calculating the minimum energy path between the metastable and stable states and evaluating the transition rate within harmonic transition state theory based on energetics obtained from density functional theory. Comparison with published experimental data shows remarkably good

Aryan Rangapur, Aman Rangapur

Large language models have gained considerable interest for their impressive performance on various tasks. Within this domain, ChatGPT and GPT-4, developed by OpenAI, and the Gemini, developed by Google, have emerged as particularly popular among early adopters. Additionally, Mixtral by Mistral AI and Claude by Anthropic are newly released, further expanding

Emilio A. Mendiola, Raza Rana Mehdi, Dipan J. Shah, Reza Avazmohammadi

Left ventricular diastolic dysfunction (LVDD) is a group of diseases that adversely affect the passive phase of the cardiac cycle and can lead to heart failure. While left ventricular end-diastolic pressure (LVEDP) is a valuable prognostic measure in LVDD patients, traditional invasive methods of measuring LVEDP present risks and limitations, highlighting th

Eric Yan

We study mechanism design settings where the planner has an interest in agents receiving noisy signals about the types of other agents. We show that additional information about other agents can eliminate undesired equilibria, making it helpful to a planner interested in full implementation, designing a mechanism for which every equilibrium outcome is desira

Tinatin Davitashvili, Hamlet Meladze, Francisco Criado-Aldeanueva, Jose Maria Sanchez

A nonlocal contact problem for two-dimensional linear elliptic equations is stated and investigated. The method of separation of variables is used to find the solution of a stated problem in case of Poisson's equation. Then the more general problem with nonlocal multipoint contact conditions for elliptic equation with variable coefficients is considered and

David Cruz-Uribe, Jacob Glidewell

Motivated by the limitations of the traditional definitions of the Riemann-Stieltjes and Darboux-Stieltjes integrals, we introduce a generalized Darboux-Stieltjes integral that is equivalent to an earlier generalization by Ross \cite{Ross}. Our definition builds upon an approach to the Darboux-Stieltjes integral recently introduced by the first author and Co

Konstantin Nestmann, Martin Leijnse, Maarten R. Wegewijs

The description of quantum transport in the strong system-reservoir coupling regime poses a significant theoretical and computational challenge that demands specialized tools for accurate analysis. RealTimeTransport is a new open-source C++ library that enables the computation of both stationary and transient transport observables for generic quantum systems

Anjanava Biswas, Wrick Talukdar

Accurate classification of multi-modal financial documents, containing text, tables, charts, and images, is crucial but challenging. Traditional text-based approaches often fail to capture the complex multi-modal nature of these documents. We propose FinEmbedDiff, a cost-effective vector sampling method that leverages pre-trained multi-modal embedding models

Ergon Cugler de Moraes Silva, Jose Carlos Vaz

What characteristics define disinformation and fake news? To address this research question, this Technical Note provides a comprehensive analysis of disinformation and fake news, synthesizing 46 definitions and highlighting four key points addressing their fundamental characteristics. Adopting the Prisma 2020 method, five search sets with the Boolean operat

Thomas Feeney, Julian Petry, Abderrezak Torche, Dirk Hauschild

Interfacial engineering has fueled recent development of p-i-n perovskite solar cells (PSCs), with self-assembled monolayer-based hole-transport layers (SAM-HTLs) enabling almost lossless contacts for solution-processed PSCs, resulting in the highest achieved power conversion efficiency (PCE) to date. Substrate interfaces are particularly crucial for the gro

Sariel Har-Peled, Rahul Saladi

$ \newcommand{\cardin}[1]{\left| {#1} \right|}% \newcommand{\Graph}{\Mh{\mathsf{G}}}% \providecommand{\G}{\Graph}% \renewcommand{\G}{\Graph}% \providecommand{\GA}{\Mh{H}}% \renewcommand{\GA}{\Mh{H}}% \newcommand{\VV}{\Mh{\mathsf{V}}}% \newcommand{\VX}[1]{\VV\pth{#1}}% \providecommand{\EE}{\Mh{\mathsf{E}}}% \renewcommand{\EE}{\Mh{\mathsf{E}}}% \newcommand{\Re

J. Hernández-Yévenes, N. Nagar, V. Arratia, T. H. Jarrett

Supermassive Black Holes (SMBHs) are commonly found at the centers of massive galaxies. Estimating their masses ($M_\text{BH}$) is crucial for understanding galaxy-SMBH co-evolution. We present WISE2MBH, an efficient algorithm that uses cataloged Wide-field Infrared Survey Explorer (WISE) magnitudes to estimate total stellar mass ($M_*$) and scale this to bu

Silvia García Méndez, Fátima Leal, Benedita Malheiro, Juan Carlos Burguillo Rial

Wiki articles are created and maintained by a crowd of editors, producing a continuous stream of reviews. Reviews can take the form of additions, reverts, or both. This crowdsourcing model is exposed to manipulation since neither reviews nor editors are automatically screened and purged. To protect articles against vandalism or damage, the stream of reviews

Renzhi Wu, Pramod Chunduri, Dristi J Shah, Ashmitha Julius Aravind

In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface. This novel interface allows users to specify object trajectory events with simple mouse drag-and-drop operations. Users can use trajectories of single objects as building blocks to compose complex events. Using

Shaoxuan Cui, Qi Zhao, Guofeng Zhang, Hildeberto Jardón-Kojakhmetov

It is known that the effect of species' density on species' growth is non-additive in real ecological systems. This challenges the conventional Lotka-Volterra model, where the interactions are always pairwise and their effects are additive. To address this challenge, we introduce HOIs (Higher-Order Interactions) which are able to capture, for example, the in

Geneviève Bélanger, Juhi Dutta, Rohini M. Godbole, Sabine Kraml

We study the connection between collider and dark matter phenomenology in the singlet extension of the Georgi-Machacek model. In this framework, the singlet scalar serves as a suitable thermal dark matter (DM) candidate. Our focus lies on the region $v_{\chi}<1$ GeV, where $v_{\chi}$ is the common vacuum expectation value of the neutral components of the sca

Matteo Farina, Gianni Franchi, Giovanni Iacca, Massimiliano Mancini

Vision-Language Models seamlessly discriminate among arbitrary semantic categories, yet they still suffer from poor generalization when presented with challenging examples. For this reason, Episodic Test-Time Adaptation (TTA) strategies have recently emerged as powerful techniques to adapt VLMs in the presence of a single unlabeled image. The recent literatu

Davor Curic, Surjeet Singh, Mojtaba Nazari, Majid H. Mohajerani

Sleep is characterized by non-rapid eye movement (nREM) sleep, originating from widespread neuronal synchrony, and REM sleep, with neuronal desynchronization akin to waking behavior. While these were thought to be global brain states, recent research suggests otherwise. Using time-frequency analysis of mesoscopic voltage-sensitive dye recordings of mice in a

Jihao Andreas Lin, Shreyas Padhy, Bruno Mlodozeniec, José Miguel Hernández-Lobato

Gaussian processes are a versatile probabilistic machine learning model whose effectiveness often depends on good hyperparameters, which are typically learned by maximising the marginal likelihood. In this work, we consider iterative methods, which use iterative linear system solvers to approximate marginal likelihood gradients up to a specified numerical pr

Jay Jasti, Hua Zhong, Vandana Panwar, Vipul Jarmale

Predictive biomarkers of treatment response are lacking for metastatic clear cell renal cell carcinoma (ccRCC), a tumor type that is treated with angiogenesis inhibitors, immune checkpoint inhibitors, mTOR inhibitors and a HIF2 inhibitor. The Angioscore, an RNA-based quantification of angiogenesis, is arguably the best candidate to predict anti-angiogenic (A

Jun Zheng, Fuwei Zhao, Youjiang Xu, Xin Dong

Video try-on stands as a promising area for its tremendous real-world potential. Prior works are limited to transferring product clothing images onto person videos with simple poses and backgrounds, while underperforming on casually captured videos. Recently, Sora revealed the scalability of Diffusion Transformer (DiT) in generating lifelike videos featuring

Takashi Kurumaji, Shiang Fang, Linda Ye, Shunsuke Kitou

Frustrated rare-earth-based intermetallics provide a promising platform for emergent magnetotransport properties through exchange coupling between conduction electrons and localized rare-earth magnetic moments. Metamagnetism, the abrupt change of magnetization under an external magnetic field, is a signature of first-order magnetic phase transitions; recentl

Shreyas Bhat, Joseph B. Lyons, Cong Shi, X. Jessie Yang

With the advent of AI technologies, humans and robots are increasingly teaming up to perform collaborative tasks. To enable smooth and effective collaboration, the topic of value alignment (operationalized herein as the degree of dynamic goal alignment within a task) between the robot and the human is gaining increasing research attention. Prior literature o

Parisa Parsamaram, Heinz Holling, Rainer Schwabe

In this paper, we develop optimal designs for growth curve models with count data based on the Rasch Poisson-Gamma counts (RPGCM) model. This model is often used in educational and psychological testing when test results yield count data. In the RPGCM, the test scores are determined by respondents ability and item difficulty. Locally D-optimal designs are de

Kejia Yin, Varshanth R. Rao, Ruowei Jiang, Xudong Liu

Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task, existing state-of-the-art (SOTA) methods (1) extract coarse features from backbones that are trained with instance-level self-supervised lea

Ihar Lobach, Michael Borland

This research introduces a novel anomaly detection method designed to enhance the operational reliability of particle accelerators - complex machines that accelerate elementary particles to high speeds for various scientific applications. Our approach utilizes a Long Short-Term Memory (LSTM) neural network to predict the temperature of key components within

Mihir Chauhan, Mohammad Abuzar Hashemi, Abhishek Satbhai, Mir Basheer Ali

We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different writer distribution. We have compared the performance of multiple generative, contrastive SSL approaches against handcrafted feature extractors a

Juliana Jaramillo-Fernandez, Martin Poblet, David Alonso-Tomás, Christian Vinther Bertelsen

Nanomechanical resonators can serve as ultrasensitive, miniaturized force probes. While vertical structures like nanopillars are ideal for this purpose, transducing their motion is challenging. Pillar-based photonic crystals (PhCs) offer a potential solution by integrating optical transduction within the pillars. However, achieving high-quality PhCs is hinde

Zhengxi Yan, Jun Xu, Jiangyong Jia

In heavy-ion phenomenology, the nucleon density distribution in colliding nuclei is commonly described by a two-parameter Woods-Saxon (WS) distribution. However, this approach overlooks the detailed radial structure in the density distribution that arises from the quantal filling patterns of neutrons and protons. These fine structures, as estimated by the Sk

Mingjun Xiang, Hui Yuan, Kai Zhou, Hartmut G. Roskos

Terahertz (THz) imaging is one of the hotspots in the field of optics, where the depth information retrieval is a key factor to restore the three-dimensional appearance of objects. Impressive results for depth extraction in visible and infrared wave range have been demonstrated through deep learning (DL). Among them, most DL methods are merely data-driven, l

Julius Degünther, Jann van der Meer, Udo Seifert

The laws of thermodynamics apply to biophysical systems on the nanoscale as described by the framework of stochastic thermodynamics. This theory provides universal, exact relations for quantities like work, which have been verified in experiments where a fully resolved description allows direct access to such quantities. Complementary studies consider partia

Bin Wang, Linke Ouyang, Fan Wu, Wenchang Ning

In the era of artificial intelligence, the diversity of data modalities and annotation formats often renders data unusable directly, requiring understanding and format conversion before it can be used by researchers or developers with different needs. To tackle this problem, this article introduces a framework called Dataset Description Language (DSDL) that

Vladimir Onoochin

In this article one aspect of the so-called '4/3-problem' is analyzed, namely definitions of the electromagnetic mass of the classical electron. It is shown that if the special relativity definition of the electromagnetic (EM) mass as the ratio of the electromagnetic field energy to the square of the speed of light is correctly treated by the scientists who

Mathieu Chevalley, Patrick Schwab, Arash Mehrjou

Targeted and uniform interventions to a system are crucial for unveiling causal relationships. While several methods have been developed to leverage interventional data for causal structure learning, their practical application in real-world scenarios often remains challenging. Recent benchmark studies have highlighted these difficulties, even when large num

Patrick Brosnan, Laura Escobar, Jaehyun Hong, Donggun Lee

We show that regular semisimple Hessenberg varieties can have moduli. To be precise, suppose $X$ is a regular semisimple Hessenberg variety of codimension $1$ in the flag variety $G/B$, where $G$ is a simple algebraic group of rank $r$ over $\mathbb{C}$ and $B$ is a Borel subgroup. We show that the space~$\mathrm{H}^1(X,TX)$ of first order deformations of $X

V. V. Bavula

The class of $\D$-locally nilpotent algebras (introduced in the paper) is a wide generalization of the algebras of differential operators on commutative algebras. Examples includes all the rings $\CD (A)$ of differential operators on commutative algebras (in arbitrary characteristic), all subalgebras of $\CD (A)$ that contain the algebra $A$, the universal e

Paul Carpentier, Nathalie Pillet, Denis Lacroix, Noel Dubray

Several protocols are proposed to build continuous energy surfaces of many-body quantum systems, regarding both energy and states. The standard variational principle is augmented with constraints on state overlap, ensuring arbitrary precision on continuity. As an illustration, the lowest energy and excited state paths relevant for the $^{240}$Pu asymmetric f

David Anton, Jendrik-Alexander Tröger, Henning Wessels, Ulrich Römer

The calibration of constitutive models from full-field data has recently gained increasing interest due to improvements in full-field measurement capabilities. In addition to the experimental characterization of novel materials, continuous structural health monitoring is another application that is of great interest. However, monitoring is usually associated

Ellen Kirkman, W. Frank Moore, Tolulope Oke

For a finite group $G$ and $\Bbbk$ an algebraically closed field of characteristic zero we consider Artin-Schelter regular algebras $A$ on which the Drinfeld double $D(G)$ acts inner faithfully, and its associated algebras of invariants $A^{D(G)}$. Explicit computations for the cases when $G$ is the (generalized) quaternion group of order 8 and 16 are given.

Nikolay Gusarov, Rajesh Mandal, Issa Salameh, Itamar Holzman

The rapid-pace growing demand for high-performance computation and big-data manipulation entails substantial increase in global power consumption, and challenging thermal management. Thus, there is a need in allocating competitive alternatives for complementary metal-oxide-semiconductor (CMOS) technologies. Superconducting platforms, such as rapid single flu

Thomas Muller, Ryan Cotterell, Alexander Fraser, Hinrich Schütze

We present LEMMING, a modular log-linear model that jointly models lemmatization and tagging and supports the integration of arbitrary global features. It is trainable on corpora annotated with gold standard tags and lemmata and does not rely on morphological dictionaries or analyzers. LEMMING sets the new state of the art in token-based statistical lemmatiz

P. J. E. Peebles

The standard LambdaCDM cosmology passes demanding tests that establish it as a good approximation to reality. It is incomplete, with open questions and anomalies, but the same is true of all our physical theories. The anomalies in the standard cosmology might guide us to an even better theory. It has happened before.

Jack Storror Carter, Manuele Leonelli, Eva Riccomagno, Gherardo Varando

Staged trees are probabilistic graphical models capable of representing any class of non-symmetric independence via a coloring of its vertices. Several structural learning routines have been defined and implemented to learn staged trees from data, under the frequentist or Bayesian paradigm. They assume a data set has been observed fully and, in practice, obs

Madhura Sondharangalla, Dan Moldovan, Raja Ayyanar

Volt-VAr control is a popular method for mitigating overvoltage violations caused by high penetration of distributed energy resources (DERs) in distribution feeders. An inherent limitation of volt-VAr control is that the reactive power (Q) absorbed/injected by the DER is determined based only on the terminal voltage, without considering the active power (P)

Amandeep Kumar, Muzammal Naseer, Sanath Narayan, Rao Muhammad Anwer

In this work, we study the problem of generating novel images from complex multimodal prompt sequences. While existing methods achieve promising results for text-to-image generation, they often struggle to capture fine-grained details from lengthy prompts and maintain contextual coherence within prompt sequences. Moreover, they often result in misaligned ima

Taillte May, Sizheng Ma, Justin L. Ripley, William E. East

The ringdown gravitational wave signal arising e.g., in the final stage of a black hole binary merger, contains important information about the properties of the remnant, and can potentially be used to perform clean tests of general relativity. However, interpreting the ringdown signal, in particular when it is the loudest, requires understanding the role of

Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades Rubio, Prayag Tiwari

The widespread use of mobile devices for all kinds of transactions makes necessary reliable and real-time identity authentication, leading to the adoption of face recognition (FR) via the cameras embedded in such devices. Progress of deep Convolutional Neural Networks (CNNs) has provided substantial advances in FR. Nonetheless, the size of state-of-the-art a

Alex Rodriguez

We show that every Jordan quadrilateral $Q\subset\mathbb{C}$ contains a disk $D$ so that $\partial D\cap\partial Q$ contains points of three different sides of $Q$. As a consequence, together with some modulus estimates from Lehto and Virtanen, we offer a short proof of the main result obtained by Chrontsios-Garitsis and Hinkkanen in 2024 and it also improve

Fekede Asefa Kumsa, Jay H. Fowke, Soheil Hashtarkhani, Brianna M. White

Prostate cancer is one of the leading causes of cancer-related mortality among men in the U.S. We examined the role of neighborhood obesogenic attributes on prostate cancer risk and mortality in the Southern Community Cohort Study (SCCS). From 34,166 SCCS male participants, 28,356 were included in the analysis. We assessed relationship between neighborhood s

Kangyao Huang, Di Guo, Xinyu Zhang, Xiangyang Ji

Training an agent to adapt to specific tasks through co-optimization of morphology and control has widely attracted attention. However, whether there exists an optimal configuration and tactics for agents in a multiagent competition scenario is still an issue that is challenging to definitively conclude. In this context, we propose competitive evolution (Com

Adda Boualem, Marwane Ayaida, Hichem Sedjelmaci, Chaimaa Khalfi

Ad-hoc networks are specifically designed to facilitate communication in environments where establishing a dedicated network infrastructure is exceedingly complex or impractical. The integration of clustering concepts into various ad-hoc network scenarios, including Wireless Sensor Networks (WSN), Mobile Ad-hoc Networks (MANET), Vehicular Ad-hoc Networks (VA

Jaskaran Singh Walia, Pavithra L K

Addressing the issue of submerged underwater trash is crucial for safeguarding aquatic ecosystems and preserving marine life. While identifying debris present on the surface of water bodies is straightforward, assessing the underwater submerged waste is a challenge due to the image distortions caused by factors such as light refraction, absorption, suspended

Manuele Leonelli, Gherardo Varando

Supervised classification is one of the most ubiquitous tasks in machine learning. Generative classifiers based on Bayesian networks are often used because of their interpretability and competitive accuracy. The widely used naive and TAN classifiers are specific instances of Bayesian network classifiers with a constrained underlying graph. This paper introdu

Luis M. Garcés-Socarrás, Amirhossein Nik, Flor Ortiz, Juan A. Vásquez-Peralvo

The Artificial Intelligence Satellite Telecommunications Testbed (AISTT), part of the ESA project SPAICE, is focused on the transformation of the satellite payload by using artificial intelligence (AI) and machine learning (ML) methodologies over available commercial off-the-shelf (COTS) AI-capable chips for onboard processing. The objectives include validat

Anchit Jain, Rozhin Nobahari, Aristide Baratin, Stefano Sarao Mannelli

Machine learning systems often acquire biases by leveraging undesired features in the data, impacting accuracy variably across different sub-populations. Current understanding of bias formation mostly focuses on the initial and final stages of learning, leaving a gap in knowledge regarding the transient dynamics. To address this gap, this paper explores the

Weitai Kang, Mengxue Qu, Jyoti Kini, Yunchao Wei

In real-life scenarios, humans seek out objects in the 3D world to fulfill their daily needs or intentions. This inspires us to introduce 3D intention grounding, a new task in 3D object detection employing RGB-D, based on human intention, such as "I want something to support my back". Closely related, 3D visual grounding focuses on understanding human refere

Ilaria Lucardesi, Davide Zucco

The P\'al inequality is a classical result which asserts that among all planar convex sets of given width the equilateral triangle is the one of minimal area. In this paper we prove three quantitative versions of this inequality, by quantifying how the closeness of the area of a convex set, of certain width, to the minimal value implies its closeness to the

Germain Vivier-Ardisson, Alexandre Forel, Axel Parmentier, Thibaut Vidal

Optimization layers in deep neural networks have enjoyed a growing popularity in structured learning, improving the state of the art on a variety of applications. Yet, these pipelines lack interpretability since they are made of two opaque layers: a highly non-linear prediction model, such as a deep neural network, and an optimization layer, which is typical

Renzhi Wang, Piji Li

Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of Large Language Models (LLMs) to various downstream applications. However, the effectiveness of the PEFT diminishes notably when downstream tasks require accurate learning of factual knowledge. In this paper, we adopt a semantic perspective to investigate this phenomenon, uncovering

Zihui Wang, Zheng Wang, Lingjuan Lyu, Zhaopeng Peng

Collaborative fairness stands as an essential element in federated learning to encourage client participation by equitably distributing rewards based on individual contributions. Existing methods primarily focus on adjusting gradient allocations among clients to achieve collaborative fairness. However, they frequently overlook crucial factors such as maintai

Lingyu Wang, Antonio La Marca, Fangyou Gao, William J. Pearson

Single-dish far-infrared (far-IR) and sub-millimetre (sub-mm) point source catalogues and their connections with catalogues at other wavelengths are of paramount importance. However, due to the large mismatch in spatial resolution, cross-matching galaxies at different wavelengths is challenging. This work aims to develop the next-generation deblended far-IR

Yuhui Wang, Miroslav Strupl, Francesco Faccio, Qingyuan Wu

Learning from multi-step off-policy data collected by a set of policies is a core problem of reinforcement learning (RL). Approaches based on importance sampling (IS) often suffer from large variances due to products of IS ratios. Typical IS-free methods, such as $n$-step Q-learning, look ahead for $n$ time steps along the trajectory of actions (where $n$ is

Daniel Freedman, Eyal Rozenberg, Alex Bronstein

A central problem in quantum mechanics involves solving the Electronic Schrodinger Equation for a molecule or material. The Variational Monte Carlo approach to this problem approximates a particular variational objective via sampling, and then optimizes this approximated objective over a chosen parameterized family of wavefunctions, known as the ansatz. Rece

Lane E. Schultz, Yiqi Wang, Ryan Jacobs, Dane Morgan

Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions. In this work, we develop a new and general approach of assessing model domain and demonstrate that our approach provides accurate and meaningful domain designation across multiple model types and material property data sets.

Mattias Wetscher, Johannes Seiler, Reto Stauffer, Nikolaus Umlauf

Forward stagewise regression is a simple algorithm that can be used to estimate regularized models. The updating rule adds a small constant to a regression coefficient in each iteration, such that the underlying optimization problem is solved slowly with small improvements. This is similar to gradient boosting, with the essential difference that the step siz

Tullio Ceccherini-Silberstein, Michel Coornaert, Xuan Kien Phung

A monoid $M$ is said to be surjunctive if every injective cellular automaton with finite alphabet over $M$ is surjective. We show that monoid algebras of surjunctive monoids are stably finite. In other words, given any field $K$ and any surjunctive monoid $M$, every one-sided invertible square matrix with entries in the monoid algebra $K[M]$ is two-sided inv

Stefan Dittmaier, Christopher Schwan, Ramon Winterhalder

We report on a recent calculation of next-to-leading-order (NLO) QCD and electroweak corrections to like-sign W-boson scattering at the Large Hadron Collider, including all partonic channels and W-boson decays in the process $pp \to e^+ \nu_e \mu^+ \nu_\mu jj + X$. The calculation is implemented in the Monte Carlo integrator Bonsay and comprises the full tow

Ruijian Han, Lan Luo, Yuanhang Luo, Yuanyuan Lin

Online statistical inference facilitates real-time analysis of sequentially collected data, making it different from traditional methods that rely on static datasets. This paper introduces a novel approach to online inference in high-dimensional generalized linear models, where we update regression coefficient estimates and their standard errors upon each ne

Nikolaos Kapouleas, Jiahua Zou

For each large enough $m\in\mathbb{N}$ we construct by PDE gluing methods a closed embedded smooth minimal hypersurface ${\breve{M}_m}$ doubling the equatorial three-sphere $\mathbb{S}_{\mathrm{eq}}^3$ in $\mathbb{S}^4(1)$, with ${\breve{M}_m}$ containing $m^2$ bridges modelled after the three-dimensional catenoid and centered at the points of a square $m\ti

Grigoriy Blekherman, Alex Dunbar

We study the convex hull of a set $S\subset \mathbb{R}^n$ defined by three quadratic inequalities. A simple way of generating inequalities valid on $S$ is to take nonnegative linear combinations of the defining inequalities of $S$. We call such inequalities aggregations. We introduce a new technique relating aggregations to properties of the spectral curve,

Antonios Valkanas, Boris N. Oreshkin, Mark Coates

Online deep learning tackles the challenge of learning from data streams by balancing two competing goals: fast learning and deep learning. However, existing research primarily emphasizes deep learning solutions, which are more adept at handling the ``deep'' aspect than the ``fast'' aspect of online learning. In this work, we introduce an alternative paradig

Bin Guo, Duong H. Phong, Jian Song, Jacob Sturm

In this short note, we remove the small degeneracy assumption in our earlier works [10, 11]. This is achieved by a technical improvement of Corollary 5.1 in [10]. As a consequence, we establish the same geometric estimates for diameter, Green's functions and Sobolev inequalities under an entropy bound for the K\"ahler metrics, without any small degeneracy as

Isadora Salles, Paola Mejia-Domenzain, Vinitra Swamy, Julian Blackwell

Clustering in education, particularly in large-scale online environments like MOOCs, is essential for understanding and adapting to diverse student needs. However, the effectiveness of clustering depends on its interpretability, which becomes challenging with high-dimensional data. Existing clustering approaches often neglect individual differences in featur

Valentina Tardugno Poleo, Nora Eisner, David W. Hogg

Differentiating between real transit events and false positive signals in photometric time series data is a bottleneck in the identification of transiting exoplanets, particularly long-period planets. This differentiation typically requires visual inspection of a large number of transit-like signals to rule out instrumental and astrophysical false positives

Subhajit Barman, Indranil Chakraborty, Sajal Mukherjee

In this article, we examine entangled quantum probes in geodesic trajectories in a flat background with a gravitational wave (GW) burst. In particular, these quantum probes are prepared initially either in the symmetric or anti-symmetric Bell's states, and we study the radiative process as the GW burst passes. We split a generic GW burst into two profiles wi

Theresia Veronika Rampisela, Tuukka Ruotsalo, Maria Maistro, Christina Lioma

Relevance and fairness are two major objectives of recommender systems (RSs). Recent work proposes measures of RS fairness that are either independent from relevance (fairness-only) or conditioned on relevance (joint measures). While fairness-only measures have been studied extensively, we look into whether joint measures can be trusted. We collect all joint

Alex B. Grilo, Philippe Lamontagne

The round complexity of interactive proof systems is a key question of practical and theoretical relevance in complexity theory and cryptography. Moreover, results such as QIP = QIP(3) (STOC'00) show that quantum resources significantly help in such a task. In this work, we initiate the study of round compression of protocols in the bounded quantum storage m

Behrad Moniri, Hamed Hassani

In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this model and identify precise phase transitions in the structure of the signal components at critical thresholds of signal strength. To demonst

Christopher Criscitiello, Quentin Rebjock, Andrew D. McRae, Nicolas Boumal

We consider the dynamics of $n$ points on a sphere in $\mathbb{R}^d$ ($d \geq 2$) which attract each other according to a function $φ$ of their inner products. When $φ$ is linear ($φ(t) = t$), the points converge to a common value (i.e., synchronize) in various connectivity scenarios: this is part of classical work on Kuramoto oscillator networks. When $φ$ i

Camilo Chacón Sartori, Christian Blum, Filippo Bistaffa, Guillem Rodríguez Corominas

Since the rise of Large Language Models (LLMs) a couple of years ago, researchers in metaheuristics (MHs) have wondered how to use their power in a beneficial way within their algorithms. This paper introduces a novel approach that leverages LLMs as pattern recognition tools to improve MHs. The resulting hybrid method, tested in the context of a social netwo

Georges Kassis

The covariance function of a Gauss-Markov process evaluated at points $(s,t)$ admits a representation as a product of a function of $\min(s,t)$ and a function of $\max(s,t)$. We call these functions the covariance factors of a Gauss-Markov process, and give the expression of the quadratic variation of a Gauss-Markov semimartingale in terms of its covariance

Ran Chen, Di Wu, Xiaowen Zhang

The Borodin-Kostochka Conjecture states that for a graph $G$, if $\Delta(G)\geq9$, then $\chi(G)\leq\max\{\Delta(G)-1,\omega(G)\}$. We use $P_t$ and $C_t$ to denote a path and a cycle on $t$ vertices, respectively. Let $C=v_1v_2v_3v_4v_5v_1$ be an induced $C_5$. A {\em $C_5^+$} is a graph obtained from $C$ by adding a $C_3=xyzx$ and a $P_2=t_1t_2$ such that

Hongyu Lu, Han-Qing Wu, Bin-Bin Chen, Zi Yang Meng

The properties of fractional Chern insulator (FCI) phases and the phase transitions between FCI and Mott insulators (MI) in bosonic systems are well studied. The continuous transitions between FCI and superfluid (SF), however, despite the inspiring field theoretical predictions, have not been directly verified. The existing numerical results of the FCI-SF tr