May 2024 arXiv papers — page 71

Abdurakhmon Sadiev, Laurent Condat, Peter Richtárik

Monotone inclusions have a wide range of applications, including minimization, saddle-point, and equilibria problems. We introduce new stochastic algorithms, with or without variance reduction, to estimate a root of the expectation of possibly set-valued monotone operators, using at every iteration one call to the resolvent of a randomly sampled operator. We

Ofer Neiman, Idan Shabat

Given an undirected weighted graph, an (approximate) distance oracle is a data structure that can (approximately) answer distance queries. A {\em Path-Reporting Distance Oracle}, or {\em PRDO}, is a distance oracle that must also return a path between the queried vertices. Given a graph on $n$ vertices and an integer parameter $k\ge 1$, Thorup and Zwick \cit

Viktor Zaverkin, Francesco Alesiani, Takashi Maruyama, Federico Errica

The ability to perform fast and accurate atomistic simulations is crucial for advancing the chemical sciences. By learning from high-quality data, machine-learned interatomic potentials achieve accuracy on par with ab initio and first-principles methods at a fraction of their computational cost. The success of machine-learned interatomic potentials arises fr

Qingxiang Liu, Xu Liu, Chenghao Liu, Qingsong Wen

Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential of language models (LMs) for time series analysis, dedicated parameters for various downstream forecasting tasks need t

Haodong Feng, Dehan Yuan, Jiale Miao, Jie You

Navigating efficiently across vortical flow fields presents a significant challenge in various robotic applications. The dynamic and unsteady nature of vortical flows often disturbs the control of underwater robots, complicating their operation in hydrodynamic environments. Conventional control methods, which depend on accurate modeling, fail in these settin

Emile Pierret, Bruno Galerne

Diffusion or score-based models recently showed high performance in image generation. They rely on a forward and a backward stochastic differential equations (SDE). The sampling of a data distribution is achieved by numerically solving the backward SDE or its associated flow ODE. Studying the convergence of these models necessitates to control four different

Nolwenn Bernard, Krisztian Balog

We present a methodology to systematically test conversational recommender systems with regards to conversational breakdowns. It involves examining conversations generated between the system and simulated users for a set of pre-defined breakdown types, extracting responsible conversational paths, and characterizing them in terms of the underlying dialogue in

Yasuhiro Nakayama, Tomochika Sawaki, Issei Furuya, Shunsuke Tamura

The purpose of this study is to estimate the correlation structure between multiple assets using financial text analysis. In recent years, as the background of elevating inflation in the global economy and monetary policy tightening by central banks, the correlation structure between assets, especially interest rate sensitivity and inflation sensitivity, has

Yilun Liu, Ruihong Qiu, Zi Huang

Large-scale graphs are valuable for graph representation learning, yet the abundant data in these graphs hinders the efficiency of the training process. Graph condensation (GC) alleviates this issue by compressing the large graph into a significantly smaller one that still supports effective model training. Although recent research has introduced various app

Akitada Sakurai, Aoi Hayashi, William John Munro, Kae Nemoto

A quadrillion dimensional Hilbert space hosted by a quantum processor with over 50 physical qubits has been expected to be powerful enough to perform computational tasks ranging from simulations of many-body physics to complex financial modeling. Despite few examples and demonstrations, it is still not clear how we can utilize such a large Hilbert space as a

Jakob Karalus

Human-in-the-loop reinforcement learning allows the training of agents through various interfaces, even for non-expert humans. Recently, preference-based methods (PbRL), where the human has to give his preference over two trajectories, increased in popularity since they allow training in domains where more direct feedback is hard to formulate. However, the c

Guoqing Tian, Ying Wu, Xin-You Lü

We theoretically predict a kind of power-law-exponential (PLE) dipole-dipole interaction between quantum emitters in a 1D waveguide QED system. This unconventional long-range interaction is the combination of power-law growth and exponential decay couplings. Applying PLE interaction to a spin model, we uncover the rich many-body phases. Most remarkably, we f

Salam Ahmed Ali, Peshraw Salam Abdulqadir, Shan Ali Abdullah, Haruna Yunusa

Malaria is a life-threatening infectious disease caused by Plasmodium parasites, which poses a significant public health challenge worldwide, particularly in tropical and subtropical regions. Timely and accurate detection of malaria parasites in blood cells is crucial for effective treatment and control of the disease. In recent years, deep learning techniqu

Chaokang Jiang, Dalong Du, Jiuming Liu, Siting Zhu

Point Cloud Interpolation confronts challenges from point sparsity, complex spatiotemporal dynamics, and the difficulty of deriving complete 3D point clouds from sparse temporal information. This paper presents NeuroGauss4D-PCI, which excels at modeling complex non-rigid deformations across varied dynamic scenes. The method begins with an iterative Gaussian

Minhaeng Cho

Stimulated Raman scattering, employing a pump and a Stokes beam, exhibits itself through both the Raman loss observed in the pump beam and the Raman gain in the Stokes beam. This phenomenon finds application in spectroscopy for chemical analyses and microscopy for label-free bioimaging studies. Recent efforts have been made to implement super-resolution Rama

Hanlin Gu, Win Kent Ong, Chee Seng Chan, Lixin Fan

The advent of Federated Learning (FL) highlights the practical necessity for the right to be forgotten for all clients, allowing them to request data deletion from the machine learning models service provider. This necessity has spurred a growing demand for Federated Unlearning (FU). Feature unlearning has gained considerable attention due to its application

Mohammed Baharoon, Jonathan Klein, Dominik L. Michels

Vision-language contrastive learning frameworks such as CLIP enable learning representations from natural language supervision and provide strong zero-shot classification capabilities. However, due to the nature of the supervisory signal in these paradigms, they lack the ability to learn localized features, leading to degraded performance on dense prediction

Duo Xu, Ye Zhu

Image segmentation plays a critical role in unlocking the mysteries of the universe, providing astronomers with a clearer perspective on celestial objects within complex astronomical images and data cubes. Manual segmentation, while traditional, is not only time-consuming but also susceptible to biases introduced by human intervention. As a result, automated

Kazuki Doi, Naoki Ogawa, Kotaro Shinmyo, Yu-ki Suzuki

In this paper we construct CFT states describing a putative holographic dual to local excitations in the three-dimensional de Sitter space (dS), called the bulk local states. We find that the conjugation operation in dS$_3/$CFT$_2$ is notably different from that in AdS$_3/$CFT$_2$. This requires us to combine two bulk local states constructed out of differen

Mohsena Ashraf

This research article explores the potential of Artificial Intelligence (AI) and Chat Generative Pre-trained Transformers (ChatGPT) in revolutionizing the landscape of parental support and child care. With the advancement of generative AI, conversational agent technology, and Large Language Models, these tools can be a great support for parents to guide and

Jaehee Ryu, Seonhee Cho, Gyubok Lee, Edward Choi

In this paper, we introduce EHR-SeqSQL, a novel sequential text-to-SQL dataset for Electronic Health Record (EHR) databases. EHR-SeqSQL is designed to address critical yet underexplored aspects in text-to-SQL parsing: interactivity, compositionality, and efficiency. To the best of our knowledge, EHR-SeqSQL is not only the largest but also the first medical t

Sheng-Chao Zhang, Man-Yu Duan, Wen-Tao Lyu, Guan-Ying Wang

Recently, the Belle and LHCb Collaborations have measured the $\Lambda^+_c \to p K^- \pi^+$ decay and reported the $p K^-$ invariant mass distribution, which shows a clear cusp structure around the $\eta \Lambda$ threshold. In this work, we have analyzed this process by considering the triangle mechanism and the $S$-wave pseudoscalar meson-octet baryon inter

Ben Kane, Sudhir Pujahari, Zichen Yang

In this paper, we consider a version of the bias conjecture for second moments in the setting of elliptic curves over finite fields whose trace of Frobenius lies in an arbitrary fixed arithmetic progression. Contrary to the classical setting of reductions of one-parameter families over the rationals, where it is conjectured by Steven J. Miller that the bias

Dusko Pavlovic

Machine-learned language models have transformed everyday life: they steer us when we study, drive, manage money. They have the potential to transform our civilization. But they hallucinate. Their realities are virtual. This note provides a high-level overview of language models and outlines a low-level model of learning machines. It turns out that, after th

Chia-Fu Liu, Lipai Huang, Kai Yin, Sam Brody

Near-real time estimation of damage to buildings and infrastructure, referred to as damage nowcasting in this study, is crucial for empowering emergency responders to make informed decisions regarding evacuation orders and infrastructure repair priorities during disaster response and recovery. Here, we introduce FloodDamageCast, a machine learning framework

Weiqi Wu, Hongqiu Wu, Lai Jiang, Xingyuan Liu

Drama is a form of storytelling inspired by human creativity, proceeding with a predefined storyline, carrying emotions and thoughts. This paper introduces \emph{LLM-based interactive drama}, which endows traditional drama with an unprecedented immersion, where a person is allowed to walk into it and interact with the characters and scenes. We define this ne

Guangyu Guo, Jiawen Yao, Yingda Xia, Tony C. W. Mok

The absence of adequately sufficient expert-level tumor annotations hinders the effectiveness of supervised learning based opportunistic cancer screening on medical imaging. Clinical reports (that are rich in descriptive textual details) can offer a "free lunch'' supervision information and provide tumor location as a type of weak label to cope with screenin

Carlotta Giannelli, Lorenzo Sacco, Alessandra Sestini, Zbyněk Šír

When a moving frame defined along a space curve is required to keep an axis aligned with the tangent direction of motion, the use of rotation-minimizing frames (RMF) avoids unnecessary rotations in the normal plane. The construction of rigid body motions using a specific subset of quintic curves with rational RMFs (RRMFs) is here considered. In particular, a

Benjamin Jany, Alberto Ravagnani

We investigate the maximum cardinality and the mathematical structure of error-correcting codes endowed with the Kendall-$\tau$ metric. We establish an averaging bound for the cardinality of a code with prescribed minimum distance, discuss its sharpness, and characterize codes attaining it. This leads to introducing the family of $t$-balanced codes in the Ke

Arvish Dabra, N. Shravan Kumar

For a locally compact group $G$ and $1 < p < \infty,$ let $B_p(G)$ denote the $p$-analog of the Fourier-Stieltjes algebra $B(G) \, (\text{or} \, B_2(G))$. Let $r: B_p(G) \to B_p(H)$ be the restriction map given by $r(u) = u|_H$ for any closed subgroup $H$ of $G.$ In this article, we prove that the restriction map $r$ is a surjective isometry for any open sub

Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang

In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL). However, state-of-the-art (SOTA) RL techniques with Temporal-Difference (TD) learning frameworks often suffer from learning inefficiency, due to the significant expansion of

Zhiyuan Liu, Yaorui Shi, An Zhang, Sihang Li

Molecule-text modeling, which aims to facilitate molecule-relevant tasks with a textual interface and textual knowledge, is an emerging research direction. Beyond single molecules, studying reaction-text modeling holds promise for helping the synthesis of new materials and drugs. However, previous works mostly neglect reaction-text modeling: they primarily f

Yao Teng, Yue Wu, Han Shi, Xuefei Ning

Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant challenges when dealing with high-resolution images. In this work, we propose Diffusion Mamba (DiM), which combines the eff

Jiwan Seo, Joonhyuk Kang

Learning discrete representations with vector quantization (VQ) has emerged as a powerful approach in various generative models. However, most VQ-based models rely on a single, fixed-rate codebook, requiring extensive retraining for new bitrates or efficiency requirements. We introduce Rate-Adaptive Quantization (RAQ), a multi-rate codebook adaptation framew

Zhibo Chen, Heming Sun, Li Zhang, Fan Zhang

This paper provides a survey of the latest developments in visual signal coding and processing with generative models. Specifically, our focus is on presenting the advancement of generative models and their influence on research in the domain of visual signal coding and processing. This survey study begins with a brief introduction of well-established genera

Bing Xue, Katsuyuki Haneda, Clemens Icheln

The study of 5G base station antenna array performance for self-interference reduction is derived. The line of sight signal channel model and Rayleigh channel model are developed. The relevant calculations for channel capacities are shown. This is the pre-material for this study. More results and conclusions will be presented soon.

Hanzhao Wang, Yu Pan, Fupeng Sun, Shang Liu

In this paper, we consider the supervised pre-trained transformer for a class of sequential decision-making problems. The class of considered problems is a subset of the general formulation of reinforcement learning in that there is no transition probability matrix; though seemingly restrictive, the subset class of problems covers bandits, dynamic pricing, a

Ryoga Miwa, Ryoi Ohashi, Satoshi Fujimoto, Takeshi Mizushima

We theoretically investigate collective excitations in the Fulde-Ferrell-Larkin-Ovchinnikov (FFLO) states of Pauli-limited superconducting films. When the long-range Coulomb interaction is absent, excitation spectra consist of two gapless and three gapped modes. The gapless modes are the Nambu-Goldstone modes associated with the spontaneous breaking of the $

Abhijeet Das

Soil is a critical component of terrestrial ecosystems, directly influencing global biogeochemical cycles. Despite its importance, the complex architecture of soil pores and their impact on greenhouse gas emissions remain poorly understood. This perspective aims to address this gap by applying discrete symmetry and symmetry-breaking concepts through fractal

Bo Fan, Zi Cai, Antonio M. García-García

We identify a time crystal phase characterized by a frequency half of the driving frequency in disordered superconductors by employing the time dependent Bogoliubov-de Gennes formalism at zero temperature with a periodically driven coupling constant. After a period of exponential increase of spatial inhomogeneities and exponential suppression of the order pa

Ding Wang, Lei-Han Tang

Fine resolution of the discrete eigenvalues at the spectral edge of an $N\times N$ random matrix is required in many applications. Starting from a finite-size scaling ansatz for the Stieltjes transform of the maximum likelihood spectrum, we demonstrate that the scaling function satisfies a first-order ODE of the Riccati type. Further transformation yields a

Alessio Buscemi, Daniele Proverbio

Democratic opinion-forming may be manipulated if newspapers' alignment to political or economical orientation is ambiguous. Various methods have been developed to better understand newspapers' positioning. Recently, the advent of Large Language Models (LLM), and particularly the pre-trained LLM chatbots like ChatGPT or Gemini, hold disruptive potential to as

Zihe Liu, Jie Lu, Guangquan Zhang, Junyu Xuan

Deep reinforcement learning is used in various domains, but usually under the assumption that the environment has stationary conditions like transitions and state distributions. When this assumption is not met, performance suffers. For this reason, tracking continuous environmental changes and adapting to unpredictable conditions is challenging yet crucial b

Yujie Lu, Xiujun Li, Tsu-Jui Fu, Miguel Eckstein

The rapid progress in Multimodal Large Language Models (MLLMs) has significantly advanced their ability to process and understand complex visual and textual information. However, the integration of multiple images and extensive textual contexts remains a challenge due to the inherent limitation of the models' capacity to handle long input sequences efficient

Haoran Li, Xinyuan Zhao, Dadi Guo, Hanlin Gu

As large language models (LLMs) demonstrate unparalleled performance and generalization ability, LLMs are widely used and integrated into various applications. When it comes to sensitive domains, as commonly described in federated learning scenarios, directly using external LLMs on private data is strictly prohibited by stringent data security and privacy re

T. Y. S. S Santosh, Tuan-Quang Vuong, Matthias Grabmair

This study investigates the challenges posed by the dynamic nature of legal multi-label text classification tasks, where legal concepts evolve over time. Existing models often overlook the temporal dimension in their training process, leading to suboptimal performance of those models over time, as they treat training data as a single homogeneous block. To ad

Hanwei Zhang, Luo Cheng, Qisong He, Wei Huang

Classification of 3D point clouds is a challenging machine learning (ML) task with important real-world applications in a spectrum from autonomous driving and robot-assisted surgery to earth observation from low orbit. As with other ML tasks, classification models are notoriously brittle in the presence of adversarial attacks. These are rooted in imperceptib

Xi Wang, Jie Liu, Jianbo Wu, Shuangyan Yang

Compute eXpress Link (CXL) is emerging as a promising memory interface technology. However, its performance characteristics remain largely unclear due to the limited availability of production hardware. Key questions include: What are the use cases for the CXL memory? What are the impacts of the CXL memory on application performance? How to use the CXL memor

Lyndon Ang, Robert Clark, Bronwyn Loong, Anders Holmberg

There is a growing trend among statistical agencies to explore non-probability data sources for producing more timely and detailed statistics, while reducing costs and respondent burden. Coverage and measurement error are two issues that may be present in such data. The imperfections may be corrected using available information relating to the population of

Sihong Shao, Yishan Wu

We consider a class of $0$-$1$ polynomial programming termed multiple choice polynomial programming (MCPP) where the constraint requires exact one component per subset of the partition to be $1$ after all the entries are partitioned. Compared to the unconstrained counterpart, there are few polyhedral studies of MCPP in general form. This paper serves as the

Guotao Liang, Baoquan Zhang, Yaowei Wang, Xutao Li

Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner. Although existing methods have shown superior performance, most methods prefer to learn a single-modal codebook (\emph{e.

Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu

Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless trial-and-error in global planning and generating hallucinatory actions in local planning due to their poor understanding of the ``re

Abdollah Masoud Darya, Muhammad Mubasshir Shaikh, Grzegorz Nykiel, Essam Ghamry

This study investigates the spatial and temporal characteristics of L1 amplitude scintillation-causing ionospheric irregularities over the Eastern Arabian Peninsula during the ascending phase of solar cycle 25 (years 2020--2023). The temporal occurrences of weak and strong scintillation were separated by sunset, with weak scintillation observed predominantly

Thao Nguyen, Tiara Torres-Flores, Changhyun Hwang, Carl Edwards

This paper presents a novel approach for predicting Power Conversion Efficiency (PCE) of Organic Photovoltaic (OPV) devices, called GLaD: synergizing molecular Graphs and Language Descriptors for enhanced PCE prediction. Due to the lack of high-quality experimental data, we collect a dataset consisting of 500 pairs of OPV donor and acceptor molecules along w

Wei Wang, Yang Tan, Jingjing Liu, Bin Liang

Acoustic waves in fluid with spin-0 nature have been long believed not to support spin Hall effect and strong orbital Hall effect that enables experimental observation. Here we report the first theoretical explication and experimental demonstration of giant acoustic geometric spin and orbital Hall effect characterized by a large transverse shift. We reveal t

Youcan Xu, Zhen Wang, Jun Xiao, Wei Liu

With the advance of diffusion models, various personalized image generation methods have been proposed. However, almost all existing work only focuses on either subject-driven or style-driven personalization. Meanwhile, state-of-the-art methods face several challenges in realizing compositional personalization, i.e., composing different subject and style con

Chunhui Zhang, Li Liu, Hao Wen, Xi Zhou

Multi-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \eg vision (RGB), depth, thermal infrared, event, language and audio, to estimate the state of an arbitrary object in a video sequence. It is of great significance for many applications such as autonomous driving and intelligent surveillance. In recent years,

Dinh Tuan Huynh

We prove that if $f\colon\mathbb{C}^p\rightarrow\mathbb{P}^n(\mathbb{C})$ is a holomorphic mapping of maximal rank whose image lies in the Fermat hypersurface of degree $d>(n+1)\max\{n-p,1\}$, then its image is contained in a linear subspace of dimension at most $\bigg[\dfrac{n-1}{2}\bigg]$. Analog in the logarithmic case is also given. Our result strengthen

Emma Clark, Kanghyun Ryu, Negar Mehr

Learning from Demonstration (LfD) can be an efficient way to train systems with analogous agents by enabling ``Student'' agents to learn from the demonstrations of the most experienced ``Teacher'' agent, instead of training their policy in parallel. However, when there are discrepancies in agent capabilities, such as divergent actuator power or joint angle c

Pang-Jin Tan, Shih-Fen Cheng, Richard Chen

Freight forwarding plays a crucial role in facilitating global trade and logistics. However, as the freight forwarding market is extremely fragmented, freight forwarders often face the issue of not being able to fill the available shipping capacity. This recurrent issue motivates the creation of various freight forwarding networks that aim at exchanging capa

Dinh Tuan Huynh

Let $\mathbf{K}$ be an algebraically closed field of arbitrary characteristic, complete with respect to a non-archimedean absolute value $|\,|$. We establish a Second Main Theorem type estimate for analytic map $f\colon \mathbf{K}\rightarrow\mathbb{P}^n(\mathbf{K})$ and a family of $n$ hypersurfaces in $\mathbb{P}^n(\mathbf{K})$ intersecting transversally an

V. Medvedev, E. Zhuzhoma

We prove that $n$-sphere $\mathbb{S}^n$, $n\geq 2$, admits structurally stable diffeomorphisms $\mathbb{S}^n\to\mathbb{S}^n$ with non-orientable expanding attractors of any topological dimension $d\in\{1,\ldots,[\frac{n}{2}]\}$ where $[x]$ is an integer part of $x$. One proves that $n$-torus $\mathbb{T}^n$, $n\geq 2$, admits structurally stable diffeomorphis

Zhenyu Wei, Yujie He, Zhanchuan Cai

RGB-D tracking significantly improves the accuracy of object tracking. However, its dependency on real depth inputs and the complexity involved in multi-modal fusion limit its applicability across various scenarios. The utilization of depth information in RGB-D tracking inspired us to propose a new method, named MDETrack, which trains a tracking network with

Sam F. L. Windels, Noel Malod-Dognin, Natasa Przulj

Random walks are widely used for mining networks due to the computational efficiency of computing them. For instance, graph representation learning learns a d-dimensional embedding space, so that the nodes that tend to co-occur on random walks (a proxy of being in the same network neighborhood) are close in the embedding space. Specific local network topolog

Huajin Zhao, Junrong Wang, Hong Mao, Jinshuang Jin

We investigate the quantum transport through a quantum dot coupled with a superconducting (SC) nanowire. By elaborating the differential conductance and current noise spectrum, we focus on the distinct characteristics of the topological Majorana bound states (MBSs) and trivial Andereev bound states (ABSs) hosted in SC wire. For MBSs with a topological qualit

He Zou, Meng'en Qin, Yu Song, Xiaohui Yang

In the realm of neural network models, the perpetual challenge remains in retaining task-relevant information while effectively discarding redundant data during propagation. In this paper, we introduce IB-AdCSCNet, a deep learning model grounded in information bottleneck theory. IB-AdCSCNet seamlessly integrates the information bottleneck trade-off strategy

Hao-Song You, Huai-Min Chen, Jian-Feng Xu, Cheng-Jun Xia

We study the properties of strangelets at finite temperature $T$, employing an equivparticle model that incorporates both linear confinement and leading-order perturbative interactions with density-dependent quark masses. The shell effects are analyzed by solving the Dirac equations for quarks within the mean-field approximation. As temperature increases, th

Yihao Huang, Chong Wang, Xiaojun Jia, Qing Guo

Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and time-consuming. Also, they have concentrated solely on optimization algorithms, overlooking the crucial role of the prompt.

Stephen James Krol, Maria Teresa Llano, Matthew Butler, Cagatay Goncu

Music has been identified as a promising medium to enhance the accessibility and experience of visual art for people who are blind or have low vision (BLV). However, composing music and designing soundscapes for visual art is a time-consuming, resource intensive process - limiting its scalability for large exhibitions. In this paper, we investigate the use o

Shantanu Singh, Ahamed Irshad, Germany Diaz De la Cruz, Boyang Zhao

Hydrogen has been identified as a clean, zero carbon, sustainable, and promising energy source for the future, and electrochemical water splitting for hydrogen production is an emission-free, efficient energy conversion technology. A major limitation of this approach is the unavailability of efficient, abundant, inexpensive catalysts, which prompts the need

Nicolas Acevedo, Carmen Cortez, Chris Brooks, Rene Kizilcec

Distribution shift is a common situation in machine learning tasks, where the data used for training a model is different from the data the model is applied to in the real world. This issue arises across multiple technical settings: from standard prediction tasks, to time-series forecasting, and to more recent applications of large language models (LLMs). Th

Shukai Duan, Heng Ping, Nikos Kanakaris, Xiongye Xiao

Computation graphs are Directed Acyclic Graphs (DAGs) where the nodes correspond to mathematical operations and are used widely as abstractions in optimizations of neural networks. The device placement problem aims to identify optimal allocations of those nodes to a set of (potentially heterogeneous) devices. Existing approaches rely on two types of architec

Alexey Golovnev

I discuss the issue of degrees of freedom in modified teleparallel gravity. These theories do have an extra structure on top of the usual (pseudo)Riemannian manifold, that of a flat parallel transport. This structure is absolutely abstract and unpredictable (pure gauge) in GR-equivalent models, however it becomes physical upon modifications. The problem is t

Jeremy McMahan

We present a novel algorithm that efficiently computes near-optimal deterministic policies for constrained reinforcement learning (CRL) problems. Our approach combines three key ideas: (1) value-demand augmentation, (2) action-space approximate dynamic programming, and (3) time-space rounding. Our algorithm constitutes a fully polynomial-time approximation s

Chenyu Huang, Peng Ye, Tao Chen, Tong He

The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention for its practicability. Existing model merging methods usually suffer from (1) significant performance degradation or (2)

Jakob T. Faber, Vikram Ravi, Stella Koch Ocker, Myles B. Sherman

We present a multi-wavelength study of the apparently non-repeating, heavily scattered fast radio burst, FRB 20221219A, detected by the Deep Synoptic Array 110 (DSA-110). The burst exhibits a moderate dispersion measure (DM) of $706.7^{+0.6}_{-0.6}$ $\mathrm{pc}~\mathrm{cm}^{-3}$ and an unusually high scattering timescale of $\tau_{\mathrm{obs}} = 19.2_{-2.7

Tatsuya Miki, Yukio Tanaka, Shun Tamura, Shintaro Hoshino

We study a superconductor Josephson junction with a Bogoliubov Fermi surface, employing McMillan's Green's function technique. The low-energy degrees of freedom are described by spinless fermions (bogolons), where the characteristic feature appears as an odd-frequency pair potential. The differential equation of the Green's function is reduced to the eigenva

Xin Tong

In this paper, we continue our study on the topologization and functional analytification in $\infty$-categorical and homotopical analytic geometry. As in our previous articles on the $\infty$-categorical extensions of certain analytic and topological contexts, we discuss the corresponding prismatic cohomological constructions after Bhatt-Lurie, Bhatt-Scholz

Yeonju Go, Dmitrii Torbunov, Timothy Rinn, Yi Huang

Artificial intelligence (AI) generative models, such as generative adversarial networks (GANs), variational auto-encoders, and normalizing flows, have been widely used and studied as efficient alternatives for traditional scientific simulations. However, they have several drawbacks, including training instability and inability to cover the entire data distri

Ulugbek Salaev

As Uzbek language is agglutinative, has many morphological features which words formed by combining root and affixes. Affixes play an important role in the morphological analysis of words, by adding additional meanings and grammatical functions to words. Inflectional endings are utilized to express various morphological features within the language. This fea

Paul Denny, Stephen MacNeil, Jaromir Savelka, Leo Porter

Providing timely and personalized feedback to large numbers of students is a long-standing challenge in programming courses. Relying on human teaching assistants (TAs) has been extensively studied, revealing a number of potential shortcomings. These include inequitable access for students with low confidence when needing support, as well as situations where

Xinman Cheng, Guanxing Fu, Xiaonyu Xia

In this paper, we study the long time behavior of an optimal liquidation problem with semimartingale strategies and external flows. To investigate the limit rigorously, we study the convergence of three BSDEs characterizing the value function and the optimal strategy, from finite horizon to infinite horizon. We find that in the long time limit the player may

Ambar Pal, René Vidal, Jeremias Sulam

Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that this property can be utilized for designing classifiers with improved robustness guarantees for $\ell_2$-bounded perturbations. Yet, it is still unclear if this observation holds

Tao Qin

In this paper, we consider the subdivision map between two KLRW algebras of type $A^{(1)}_e$ and $A^{(1)}_{e+1}$. We show that the image of an idempotent indexed by a partition under this map is still an idempotent indexed by a partition, and give the form of this new partition. Moreover, we give an equality of some graded decomposition numbers.

Yuheng Shi, Minjing Dong, Chang Xu

Despite the significant achievements of Vision Transformers (ViTs) in various vision tasks, they are constrained by the quadratic complexity. Recently, State Space Models (SSMs) have garnered widespread attention due to their global receptive field and linear complexity with respect to the input length, demonstrating substantial potential across fields inclu

Shenghui Chen, Daniel Fried, Ufuk Topcu

Developing autonomous agents that can strategize and cooperate with humans under information asymmetry is challenging without effective communication in natural language. We introduce a shared-control game, where two players collectively control a token in alternating turns to achieve a common objective under incomplete information. We formulate a policy syn

Arghavan Jalayer, Masoud Jalayer, Mehdi Khakzand, Mohsen Faizi

Overpopulation in animal shelters contributes to increased disease spread and higher expenses on animal healthcare, leading to fewer adoptions and more shelter deaths. Additionally, one of the greatest challenges that shelters face is the noise level in the dog kennel area, which is physically and physiologically hazardous for both animals and staff. This pa

Zipeng Qi, Chenyang Liu, Zili Liu, Hao Chen

Multi-view segmentation in Remote Sensing (RS) seeks to segment images from diverse perspectives within a scene. Recent methods leverage 3D information extracted from an Implicit Neural Field (INF), bolstering result consistency across multiple views while using limited accounts of labels (even within 3-5 labels) to streamline labor. Nonetheless, achieving s

Jiapu Wang, Kai Sun, Linhao Luo, Wei Wei

Temporal Knowledge Graph Reasoning (TKGR) is the process of utilizing temporal information to capture complex relations within a Temporal Knowledge Graph (TKG) to infer new knowledge. Conventional methods in TKGR typically depend on deep learning algorithms or temporal logical rules. However, deep learning-based TKGRs often lack interpretability, whereas rul

Nhat Chung, Sensen Gao, Tuan-Anh Vu, Jie Zhang

Vision-Large-Language-Models (Vision-LLMs) are increasingly being integrated into autonomous driving (AD) systems due to their advanced visual-language reasoning capabilities, targeting the perception, prediction, planning, and control mechanisms. However, Vision-LLMs have demonstrated susceptibilities against various types of adversarial attacks, which woul

Cathy Xuanchi Liu, Tristram J. Alexander, Eduardo G. Altmann

Large complex networks are often organized into groups or communities. In this paper, we introduce and investigate a generative model of network evolution that reproduces all four pairwise community types that exist in directed networks: assortative, core-periphery, disassortative, and the newly introduced source-basin type. We fix the number of nodes and th

Qishi Zhan, Dan Sun, Erdi Gao, Yuhan Ma

This study introduces a novel unsupervised medical image feature extraction method that employs spatial stratification techniques. An objective function based on weight is proposed to achieve the purpose of fast image recognition. The algorithm divides the pixels of the image into multiple subdomains and uses a quadtree to access the image. A technique for t

Katherine E. Stange

Let $E$ be an elliptic curve with complex multiplication by a ring $R$, where $R$ is an order in an imaginary quadratic field or quaternion algebra. We define sesquilinear pairings ($R$-linear in one variable and $R$-conjugate linear in the other), taking values in an $R$-module, generalizing the Weil and Tate-Lichtenbaum pairings.

Takuya Yoshimoto, Satoru Shinoda, Kouji Yamamoto, Kouji Tahata

In oncology, phase II or multiple expansion cohort trials are crucial for clinical development plans. This is because they aid in identifying potent agents with sufficient activity to continue development and confirm the proof of concept. Typically, these clinical trials are single-arm trials, with the primary endpoint being short-term treatment efficacy. De

Qinghua He, Jie Zhang, Shengdan Tao, Hai-yao Deng

Nonsymmorphic symmetries can enforce band connectivity that obstructs a single-band Wannier description. We show that a fractional translation $\mathcal{L}$ connecting distinct high-symmetry Wyckoff positions generically renders the Wannier center of an individual band gauge ill-defined, requiring a symmetry-enforced multiband object -- a Wannier complex. We

Yuxiang Hu, Haowei Yang, Ting Xu, Shuyao He

The diagnosis of brain cancer relies heavily on medical imaging techniques, with MRI being the most commonly used. It is necessary to perform automatic segmentation of brain tumors on MRI images. This project intends to build an MRI algorithm based on U-Net. The residual network and the module used to enhance the context information are combined, and the voi

Mahieddine Adim, Roberta Bianchini, Vincent Duchêne

We rigorously justify the bilayer shallow-water system as an approximation to the hydrostatic Euler equations in situations where the flow is density-stratified with close-to-piecewise constant density profiles, and close-to-columnar velocity profiles. Our theory accommodates with continuous stratification, so that admissible deviations from bilayer profiles

Takaaki Nomura, Yusuke Shimizu, Towa Takahashi

We study a relic density of the flavino dark matter in modified Altarelli and Feruglio $A_4$ model which is respecting the $SU(2)_L\times A_4\times Z_3\times U(1)_R$ symmetry. We calculate the Lagrangian from the superpotential in the model. In estimating relic density, we consider the relevant interactions from the Lagrangian that realize the vacuum expecta

Yafeng Yan, Shuyao He, Zhou Yu, Jiajie Yuan

Aiming at the limitations of traditional medical decision system in processing large-scale heterogeneous medical data and realizing highly personalized recommendation, this paper introduces a personalized medical decision algorithm utilizing graph neural network (GNN). This research innovatively integrates graph neural network technology into the medical and

Taylor Archibald, Tony Martinez

Efficient categorization of historical documents is crucial for fields such as genealogy, legal research, and historical scholarship, where manual classification is impractical for large collections due to its labor-intensive and error-prone nature. To address this, we propose a representational learning strategy that integrates semantic segmentation and dee