May 2024 arXiv papers — page 26

Matthew Fahrbach, Srikumar Ramalingam, Morteza Zadimoghaddam, Sara Ahmadian

This work studies a novel subset selection problem called max-min diversification with monotone submodular utility ($\textsf{MDMS}$), which has a wide range of applications in machine learning, e.g., data sampling and feature selection. Given a set of points in a metric space, the goal of $\textsf{MDMS}$ is to maximize $f(S) = g(S) + \lambda \cdot \texttt{di

Richard H. Moulton, Gary A. McCully, John D. Hastings

In the rapidly evolving field of cybersecurity, ensuring the reproducibility of AI-driven research is critical to maintaining the reliability and integrity of security systems. This paper addresses the reproducibility crisis within the domain of adversarial robustness -- a key area in AI-based cybersecurity that focuses on defending deep neural networks agai

Liwei Yuan, Hideaki Ishii

We study the problem of resilient average consensus in multi-agent systems where some of the agents are subject to failures or attacks. The objective of resilient average consensus is for non-faulty/normal agents to converge to the average of their initial values despite the erroneous effects from malicious agents. To this end, we propose a successful distri

Jordi Armengol-Estapé, Vincent Michalski, Ramnath Kumar, Pierre-Luc St-Charles

Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross-modal learning can improve representations for few-shot classification. More specifically, language is a rich modality that can be used to guide visual learning. In this work, we experiment with a multi-modal architectu

Jiachen Li, Weixi Feng, Tsu-Jui Fu, Xinyi Wang

Diffusion-based text-to-video (T2V) models have achieved significant success but continue to be hampered by the slow sampling speed of their iterative sampling processes. To address the challenge, consistency models have been proposed to facilitate fast inference, albeit at the cost of sample quality. In this work, we aim to break the quality bottleneck of a

Hirofumi Tsuruta, Hiroyuki Yamazaki, Ryota Maeda, Ryotaro Tamura

Antibodies are crucial proteins produced by the immune system to eliminate harmful foreign substances and have become pivotal therapeutic agents for treating human diseases. To accelerate the discovery of antibody therapeutics, there is growing interest in constructing language models using antibody sequences. However, the applicability of pre-trained langua

John Bistlinea, Chikara Onda, Morgan Browning, Johannes Emmerling

With companies, states, and countries targeting net-zero emissions around midcentury, there are questions about how these targets alter household welfare and finances, including distributional effects across income groups. This paper examines the distributional dimensions of technology transitions and net-zero policies with a focus on welfare impacts across

Omar F. Ramadan, Jeremy Sakstein, David Rubin

The DESI collaboration have recently analyzed their first year of data, finding a preference for thawing dark energy scenarios when using parameterized equations of state for dark energy. We investigate whether this preference persists when the data is analyzed within the context of a well-studied field theory model of thawing dark energy, exponential quinte

Satwik Kundu, Swaroop Ghosh

The high expenses imposed by current quantum cloud providers, coupled with the escalating need for quantum resources, may incentivize the emergence of cheaper cloud-based quantum services from potentially untrusted providers. Deploying or hosting quantum models, such as Quantum Neural Networks (QNNs), on these untrusted platforms introduces a myriad of secur

Kun Huang, Fanglue Zhang, Neil Dodgson

The presence of spherical distortion in equirectangular projection (ERP) images presents a persistent challenge in dense regression tasks such as surface normal estimation. Although it may appear straightforward to repurpose architectures developed for 360{\deg} depth estimation, our empirical findings indicate that such models yield suboptimal performance w

Fei Zheng, Chaochao Chen, Zhongxuan Han, Xiaolin Zheng

The emergence of ChatGPT marks the arrival of the large language model (LLM) era. While LLMs demonstrate their power in a variety of fields, they also raise serious privacy concerns as the users' queries are sent to the model provider. On the other side, deploying the LLM on the user's device will also leak all the model data. Existing methods based on secur

Kohei Muramatsu, Sakie Suzuki, Koki Taguchi

The Matveev-Piergallini (MP) moves on spines of $3$-manifolds are well-known for their correspondence to the Pachner $2$-$3$ moves in dual ideal triangulations. Benedetti and Petronio introduced combinatorial descriptions of closed $3$-manifolds and combed $3$-manifolds by using branched spines and their equivalence relations, which involve MP moves with 16

Reed Perkins, Dan Ventura

We outline a solution to the challenge of musical phrase segmentation that uses grammatical induction algorithms, a class of algorithms which infer a context-free grammar from an input sequence. We analyze the performance of five grammatical induction algorithms on three datasets using various musical viewpoint combinations. Our experiments show that the LON

Xiao Peng, Tao Liu, Ying Wang

Large language models (LLMs) like ChatGPT, Gemini, or LLaMA have been trending recently, demonstrating considerable advancement and generalizability power in countless domains. However, LLMs create an even bigger black box exacerbating opacity, with interpretability limited to few approaches. The uncertainty and opacity embedded in LLMs' nature restrict thei

Jialiang Xu, Michael Moor, Jure Leskovec

Despite impressive advances in recent multimodal large language models (MLLMs), state-of-the-art models such as from the GPT-4 suite still struggle with knowledge-intensive tasks. To address this, we consider Reverse Image Retrieval (RIR) augmented generation, a simple yet effective strategy to augment MLLMs with web-scale reverse image search results. RIR r

Texture Lin

Due to the excellent physical properties, two dimensional materials have attracted widespread attention from researchers. In this article, we discuss a transition metal dichalcogenide, ReSeS monolayer with 1T" phase, with extremely low symmetry through the first principles calculation. It belongs to the space group P1 and has Jauns structure. Due to the brok

Mulei Ma, Chenyu Gong, Liekang Zeng, Yang Yang

Federated Learning (FL) has emerged as a fundamental learning paradigm to harness massive data scattered at geo-distributed edge devices in a privacy-preserving way. Given the heterogeneous deployment of edge devices, however, their data are usually Non-IID, introducing significant challenges to FL including degraded training accuracy, intensive communicatio

Sara Dastan, Demin Zhou, Takuya Ishibashi, Emanuel Karantzoulis

Longitudinal impedances at high frequencies, which extend far beyond the width of the beam spectrum, can pose a threat to the performance of modern low-emittance electron storage rings, as they can establish a relatively low threshold for microwave instability. In such rings, coherent synchrotron radiation (CSR) emerges as a prominent contributor to these hi

Hanlong Li, Pei Wang, Yuhan Wu, Jing Ren

Wood-leaf classification is an essential and fundamental prerequisite in the analysis and estimation of forest attributes from terrestrial laser scanning (TLS) point clouds,including critical measurements such as diameter at breast height(DBH),above-ground biomass(AGB),wood volume.To address this,we introduce the Wood-Leaf Classification Network(WLC-Net),a d

Zugang Mao, Amir R. Farkoosh, David N. Seidman

TThe effects of alloying elements on diffusion pathways and migration energies of interstitial carbon in austenite (f.c.c.) and ferrite (b.c.c.) are studied using density functional theory first-principles calculations. The binding energies between carbon and alloying elements are determined through 6th nearest-neighbor (NN) distances. The elements studied a

Yangyao Chen, Houjun Mo, Huiyuan Wang

We develop a model of globular cluster (GC) formation within the cosmological hierarchy of structure formation. The model is rooted in the `two-phase' scenario of galaxy formation developed in Paper-I, where the fast accretion of dark matter halos at high redshift leads to the formation of self-gravitating, turbulent gas clouds that subsequently fragment int

Sifan Zhou, Zhihang Yuan, Dawei Yang, Ziyu Zhao

Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead, making them suitable for onboard deployment and quantization. However, existing pillar-based detectors still

Noah Adhikari, Allen Gu

We show that multi-agent reinforcement learning (MARL) with full parameter sharing outperforms independent and partially shared architectures in the competitive perfect-information homogenous game of Chinese Checkers. To run our experiments, we develop a new MARL environment: variable-size, six-player Chinese Checkers. This custom environment was developed i

Yeoneung Kim, Gihun Kim, Jiwhan Park, Insoon Yang

We propose a novel Thompson sampling algorithm that learns linear quadratic regulators (LQR) with a Bayesian regret bound of $O(\sqrt{T})$. Our method leverages Langevin dynamics with a carefully designed preconditioner and incorporates a simple excitation mechanism. We show that the excitation signal drives the minimum eigenvalue of the preconditioner to gr

S. Mostafa Mousavi, Marc Stogaitis, Tajinder Gadh, Richard M Allen

This paper presents a novel approach to extract scientifically valuable information about Earth's physical phenomena from unconventional sources, such as multi-modal social media posts. Employing a state-of-the-art large language model (LLM), Gemini 1.5 Pro (Reid et al. 2024), we estimate earthquake ground shaking intensity from these unstructured posts. The

Ziqing Xing, Zhaoyang Zhang, Zirui Chen, Yusong Wang

Recently, studies have shown the potential of integrating field-type iterative methods with deep learning (DL) techniques in solving inverse scattering problems (ISPs). In this article, we propose a novel Variational Born Iterative Network, namely, VBIM-Net, to solve the full-wave ISPs with significantly improved structural rationality and inversion quality.

Jay Best, Amin Fakhari

Most robotic hands and grippers rely on actuators with large gearboxes and force sensors for controlling gripping force. However, this might not be ideal for tasks that require the robot to interact with an unstructured and unknown environment. In this paper, we introduce a novel quasi-direct-drive two-fingered robotic hand with variable impedance control in

Tianle Zhang, Jiayi Guan, Lin Zhao, Yihang Li

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for offline RL issues. However, previous offline RL algorithms based on diffusion policies generally adopt weighted regression

Corinne Powers

Automated market makers with concentrated liquidity capabilities are programmable at the tick level. The maximization of earned fees, plus depreciated reserves, is a convex optimization problem whose vector solution gives the best provision of liquidity at each tick under a given set of parameter estimates for swap volume and price volatility. Surprisingly,

Huanshuo Liu, Hao Zhang, Zhijiang Guo, Jing Wang

Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive RAG enhances this approach by enabling dynamic retrieval during generation, activating retrieval only when the query exceeds LLM's internal knowledge. Existing methods primarily foc

Che Liu, Changde Du, Xiaoyu Chen, Huiguang He

Drawing inspiration from the hierarchical processing of the human auditory system, which transforms sound from low-level acoustic features to high-level semantic understanding, we introduce a novel coarse-to-fine audio reconstruction method. Leveraging non-invasive functional Magnetic Resonance Imaging (fMRI) data, our approach mimics the inverse pathway of

Jiajie Li, Bo Gu, Shimin Gong, Zhou Su

Mobile crowdsensing (MCS) has emerged as a prominent trend across various domains. However, ensuring the quality of the sensing data submitted by mobile users (MUs) remains a complex and challenging problem. To address this challenge, an advanced method is needed to detect low-quality sensing data and identify malicious MUs that may disrupt the normal operat

Linjia Kang, Songhua Zhou, Shuyan Fang, Shichao Liu

Accurate prediction of molecular properties is crucial in drug discovery. Traditional methods often overlook that real-world molecules typically exhibit multiple property labels with complex correlations. To this end, we propose a novel framework, HiPM, which stands for hierarchical prompted molecular representation learning framework. HiPM leverages task-aw

Yonghong Li, Xiuzhuang Zhou

While existing depression prediction methods based on deep learning show promise, their practical application is hindered by the lack of trustworthiness, as these deep models are often deployed as black box models, leaving us uncertain on the confidence of their predictions. For high-risk clinical applications like depression prediction, uncertainty quantifi

Bingqian Lin, Yunshuang Nie, Ziming Wei, Yi Zhu

Vision-Language Navigation (VLN) requires the agent to follow language instructions to reach a target position. A key factor for successful navigation is to align the landmarks implied in the instruction with diverse visual observations. However, previous VLN agents fail to perform accurate modality alignment especially in unexplored scenes, since they learn

Wei Jiang, Guihong Huang, Zhen Liu, Wuming Luo

Photomultiplier tubes (PMTs) are widely used in particle experiments for photon detection. PMT waveform analysis is crucial for high-precision measurements of the position and energy of incident particles in liquid scintillator (LS) detectors. A key factor contributing to the energy resolution in large liquid scintillator detectors with PMTs is the charge sm

Olga Golovneva, Tianlu Wang, Jason Weston, Sainbayar Sukhbaatar

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by position, such as attending to the i-th token. However, current PE methods use token counts to derive position, and thus cann

Fengshuo Bai, Mingzhi Wang, Zhaowei Zhang, Boyuan Chen

With recent advancements in large language models (LLMs), alignment has emerged as an effective technique for keeping LLMs consensus with human intent. Current methods primarily involve direct training through Supervised Fine-tuning (SFT) or Reinforcement Learning from Human Feedback (RLHF), both of which require substantial computational resources and exten

Tianqi Xu, Yushuai Liu, Yuanmao Pu, Yongxiang Yang

Scandium-doped aluminum nitride (AlScN) with an asymmetric hexagonal wurtzite structure exhibits enhanced second-order nonlinear and piezoelectric properties compared to aluminum nitride (AlN), while maintaining a relatively large bandgap. It provides a promising platform for photonic integration and facilitates the seamless integration of passive and active

Chaitat Utintu, Yi-Zhe Song

We introduce SketchDeco, a training-free approach to sketch colourisation that bridges the gap between professional design needs and intuitive, region-based control. Our method empowers artists to use simple masks and colour palettes for precise spatial and chromatic specification, avoiding both the tediousness of manual assignment and the ambiguity of text-

Weining Ren, Zihan Zhu, Boyang Sun, Jiaqi Chen

Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting changes. Existing methods manage controlled environments and low occlusion ratios but fall short in rende

Ulrich D. Jentschura

The calculation of higher-order binding corrections to bound systems is a fundamental problem of theoretical physics. For any nonrelativistic expansion, one needs the Foldy-Wouthuysen Transformation which disentangles the particle and the antiparticle degrees of freedom. This transformation is carried out here to eighth order in the momenta, or, to eighth or

Zhi Li, Xiankui Meng, Jiafu Ning, Xiangyu Zhou

In this paper, we present a converse to a version of Skoda's $L^2$ division theorem by investigating the solvability of $\bar{\partial}$ equations of a specific type.

Guangrui Zhang, Zhaohui Liu, Xinghuo Yu, Mahdi Jalili

Identifying the most influential driver nodes to guarantee the fastest synchronization speed is a key topic in pinning control of multi-agent systems. This paper develops a methodology to find the most influential pinning nodes under time-varying topologies. First, we provide the pinning control synchronization conditions of multi-agent systems. Second, a me

Zhihui Xie, Jizhou Guo, Tong Yu, Shuai Li

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious mistakes and contradictions, raising doubts about their ability to robustly process and utilize generated rationales. In this w

Joonhyung Lee, Jeongin Bae, Byeongwook Kim, Se Jung Kwon

The massive computational costs associated with large language model (LLM) pretraining have spurred great interest in reduced-precision floating-point representations to accelerate the process. As a result, the BrainFloat16 (BF16) precision has become the de facto standard for LLM training, with hardware support included in recent generations of accelerators

Tianyu Zhu, Linqing Peng, Huanchen Zhai, Zhi-Hao Cui

The Kondo effect is a prototypical quantum phenomenon arising from the interaction between localized electrons in a magnetic impurity and itinerant electrons in a metallic host. Although it has served as the testing ground for quantum many-body methods for decades, the precise description of Kondo physics with material specificity remains challenging. Here,

Runlong Yu, Qixiang Shao, Qi Liu, Huan Liu

Feature interaction selection is a fundamental problem in commercial recommender systems. Most approaches equally enumerate all features and interactions by the same pre-defined operation under expert guidance. Their recommendation is unsatisfactory sometimes due to the following issues: (1)~They cannot ensure the learning abilities of models because their a

Xianke Qiang, Zheng Chang, Yun Hu, Lei Liu

Vehicular edge intelligence (VEI) is a promising paradigm for enabling future intelligent transportation systems by accommodating artificial intelligence (AI) at the vehicular edge computing (VEC) system. Federated learning (FL) stands as one of the fundamental technologies facilitating collaborative model training locally and aggregation, while safeguarding

You Huang, Zongyu Lan, Liujuan Cao, Xianming Lin

The Segment Anything Model (SAM) marks a notable milestone in segmentation models, highlighted by its robust zero-shot capabilities and ability to handle diverse prompts. SAM follows a pipeline that separates interactive segmentation into image preprocessing through a large encoder and interactive inference via a lightweight decoder, ensuring efficient real-

Sihong Shao, Chuan Yang

The existing inverse power ($\mathbf{IP}$) method for solving the balanced graph cut lacks local convergence and its inner subproblem requires a nonsmooth convex solver. To address these issues, we develop a simple inverse power ($\mathbf{SIP}$) method using a novel equivalent continuous formulation of the balanced graph cut, and its inner subproblem allows

Yiou Zhang, Shashi Pandey, Sergei Ivanov, Jian Liu

SrIrO$_3$ is a metallic complex oxide with unusual electronic and magnetic properties believed to originate from electron correlations due to its proximity to Mott metal-insulator transition. However, the nature of its electronic state and the mechanism of metallic conduction remain poorly understood. We demonstrate that shot noise produced by nanoscale SrIr

Tyler Becker, Zachary Sunberg

Many real-world decision problems involve the interaction of multiple self-interested agents with limited sensing ability. The partially observable stochastic game (POSG) provides a mathematical framework for modeling these problems, however solving a POSG requires difficult reasoning over two critical factors: (1) information revealed by partial observation

Kazuo Fujikawa, Anca Tureanu

The commonly used pseudo-C symmetry $(\nu_{L})^{c}=C\overline{\nu_{L}}^{T}$ is not defined in Lagrangian field theory. In general, there exist two classes of Majorana fermions; the first is associated with the Dirac-type fermion with the conventional C and P symmetries, and the second is associated with the Weyl-type fermion defined by CP symmetry only and f

Jeongwan Kang, Seung-Woo Ko, Sunwoo Kim

In this paper, we propose two-dimensional signal path classification (2D-SPC) for reconfigurable intelligent surface (RIS)-assisted near-field (NF) localization. In the NF regime, multiple RIS-driven signal paths (SPs) can contribute to precise localization if these are decomposable and the reflected locations on the RIS are known, referred to as SP decompos

Xuehao Gao, Yang Yang, Yang Wu, Shaoyi Du

Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one's intention. While many fruitful efforts have been made to human motion prediction, most approaches focus on pose-driven prediction and inferring human motion in isolation from the contextual environment, thus leaving the body location move

Haiqing Xu, Jiangtao Su, Suo Liu, Yuanyong Deng

The magnetic field inside the sunspot umbra, as observed by the Full-disk MagnetoGraph (FMG) onboard the Advanced Space based Solar Observatory (ASO-S), was found to be experiencing a weakening. To address this issue, we employed a method developed by Xu et al. (2021) to correct the weakening in the data of 20 active regions observed by FMG during the period

Dohyeong Kim, Taehyun Cho, Seungyub Han, Hojun Chung

The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-based constraints. However, the nonlinearity of risk measures makes it challenging to achieve convergence and optimality. To overcome the difficulties posed by the nonlinearity, we pro

Wei Kou, Xurong Chen

The relationship between QCD and the string model offers a valuable perspective for exploring the interaction potential between quarks. In this study, we investigate the restoration of chiral symmetry in connection with the Unruh effect experienced by accelerating observers. Utilizing the Schwinger model, we analyze the critical point at which the string or

Shuo Li

We prove that, for any pure morphic word $w$, if the frequencies of all letters in $w$ exist, then the frequencies of all factors in $w$ exist as well. This result answers a question of Saari in his doctoral thesis.

Siddharth Padmanabhan, Kazuki Miyazawa, Takato Horii, Takayuki Nagai

There are several challenges in developing a model for multi-tasking humanoid control. Reinforcement learning and imitation learning approaches are quite popular in this domain. However, there is a trade-off between the two. Reinforcement learning is not the best option for training a humanoid to perform multiple behaviors due to training time and model size

Jieming Ke, Xiaodong Lu, Yanlong Zhao, Ji-Feng Zhang

The paper investigates the distributed estimation problem under low bit rate communications. Based on the signal-comparison (SC) consensus protocol under binary-valued communications, a new consensus+innovations type distributed estimation algorithm is proposed. Firstly, the high-dimensional estimates are compressed into binary-valued messages by using a per

Abishek Sriramulu, Nicolas Fourrier, Christoph Bergmeir

Graph Neural Networks (GNN) have gained significant traction in the forecasting domain, especially for their capacity to simultaneously account for intra-series temporal correlations and inter-series relationships. This paper introduces a novel Hierarchical GNN (DeepHGNN) framework, explicitly designed for forecasting in complex hierarchical structures. The

Yufeng Zhou, Wen Chen, Qingqing Wu, Xusheng Zhu

This paper investigates a novel communication paradigm employing movable antennas (MAs) within a multiple-input single-output (MISO) non-orthogonal multiple access (NOMA) downlink framework, where users are equipped with MAs. Initially, leveraging the far-field response, we delineate the channel characteristics concerning both the power allocation coefficien

Dilara Siraeva

We applied a method of symmetry reduction to the gas dynamics equations with a special form of the equation of state. This equation of state is a pressure represented as the sum of a density and an entropy functions. The symmetry Lie algebra of the system is 12-dimensional. One, two and three-dimensional subalgebras were considered. In this article, four-dim

Kaixiang Zhang, Yongqiang Wang, Ziyou Song, Zhaojian Li

Distributed model predictive control (DMPC) has attracted extensive attention as it can explicitly handle system constraints and achieve optimal control in a decentralized manner. However, the deployment of DMPC strategies generally requires the sharing of sensitive data among subsystems, which may violate the privacy of participating systems. In this paper,

Valentin V. Khoze

We consider all magnetic monopoles that could have settled in the Standard Model after descending from a generic microscopic theory. These monopoles have Standard Model quantum numbers, are stable, and we also require that their magnetic fluxes are consistent with the electroweak symmetry breaking. Scattering processes involving quarks, leptons and protons o

Fengshuo Bai, Rui Zhao, Hongming Zhang, Sijia Cui

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems from the learning loop, which entails accurate reward learning compounded with value/policy learning, necessitating a consi

Arpita Soni, Sujatha Alla, Suresh Dodda, Hemanth Volikatla

The market for domestic robots made to perform household chores is growing as these robots relieve people of everyday responsibilities. Domestic robots are generally welcomed for their role in easing human labor, in contrast to industrial robots, which are frequently criticized for displacing human workers. But before these robots can carry out domestic chor

Danick Lamoureux, Sophie Ramananarivo, David Melancon, Frédérick P. Gosselin

Developing engineering systems that rely on flow-induced reconfiguration, the phenomenon where a structure deforms under flow to reduce its drag, requires design tools that can predict the behavior of these flexible structures. Current methods include using fully coupled computational fluid dynamics and finite element analysis solvers or highly specialized t

Alexander Soen, Hisham Husain, Philip Schulz, Vu Nguyen

Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. The predominant approach is to alter the supervised learning pipeline by augmenting typical loss functions, letting model rejection incur a lower loss than an incorrect prediction. Instead, we propose a different distributional perspective, wh

Marko Mićić, Jimmy A. Irwin, Preethi Nair, Brenna N. Wells

The existence of high-$z$ over-massive supermassive black holes represents a major conundrum in our understanding of black hole evolution. In this paper, we probe from the observational point of view how early Universe environmental conditions could have acted as an evolutionary mechanism for the accelerated growth of the first black holes. Under the assumpt

Mohammadjavad Matinkia, Nilanjan Ray

Diffeomorphic image registration (DIR) is a fundamental task in 3D medical image analysis that seeks topology-preserving deformations between image pairs. To ensure diffeomorphism, a common approach is to model the deformation field as the flow map solution of a differential equation, which is solved using efficient schemes such as scaling and squaring along

Hayden McAlister, Anthony Robins, Lech Szymanski

The Dense Associative Memory generalizes the Hopfield network by allowing for sharper interaction functions. This increases the capacity of the network as an autoassociative memory as nearby learned attractors will not interfere with one another. However, the implementation of the network relies on applying large exponents to the dot product of memory vector

Sejoong Kim

In this work, we investigate the electronic and magnetic properties of single-layer pentahexoctite, a two-dimensional carbon allotrope patterned by pentagons, hexagons, and octagons. Using density functional theory (DFT) calculations incorporating on-site and intersite Coulomb interactions, we find that type-II Dirac Fermions are formed by a nearly flat band

Shubham Vatsal, Ayush Singh

Large language models (LLMs) have shown remarkable performance on many tasks in different domains. However, their performance in closed-book biomedical machine reading comprehension (MRC) has not been evaluated in depth. In this work, we evaluate GPT on four closed-book biomedical MRC benchmarks. We experiment with different conventional prompting techniques

Antonio A. Chaves, Mauricio G. C. Resende, Ricardo M. A. Silva

This paper proposes a problem-independent GRASP metaheuristic using the random-key optimizer (RKO) paradigm. GRASP (greedy randomized adaptive search procedure) is a metaheuristic for combinatorial optimization that repeatedly applies a semi-greedy construction procedure followed by a local search procedure. The best solution found over all iterations is ret

Haya Diwan, Jinrui Gou, Cameron Musco, Christopher Musco

There has been significant recent interest in graph-based nearest neighbor search methods, many of which are centered on the construction of navigable graphs over high-dimensional point sets. A graph is navigable if we can successfully move from any starting node to any target node using a greedy routing strategy where we always move to the neighbor that is

Hayden McAlister, Anthony Robins, Lech Szymanski

We discuss prototype formation in the Hopfield network. Typically, Hebbian learning with highly correlated states leads to degraded memory performance. We show this type of learning can lead to prototype formation, where unlearned states emerge as representatives of large correlated subsets of states, alleviating capacity woes. This process has similarities

Juntao Zhang, Shaogeng Liu, Jun Zhou, Kun Bian

In recent years, State Space Models (SSMs) with efficient hardware-aware designs, known as the Mamba deep learning models, have made significant progress in modeling long sequences such as language understanding. Therefore, building efficient and general-purpose visual backbones based on SSMs is a promising direction. Compared to traditional convolutional ne

A-Ming Liu, Andrey V. Vasil'ev

Given a set of primes $\pi$, the $\pi$-index of an element $x$ of a finite group $G$ is the $\pi$-part of the index of the centralizer of $x$ in $G$. If $\pi=\{p\}$ is a singleton, we just say the $p$-index. If the $\pi$-index of $x$ is equal to $p_1^{k_1}\ldots p^{k_s}$, where $p_1,\ldots,p_s$ are distinct primes, then we set $\exp_\pi(x)=k_1+\ldots+k_s$. I

Ido Sobol, Chenfeng Xu, Or Litany

Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce to immersive virtual experiences. Recent advancements in diffusion models, particularly the Zero-1-to-3 model, have been widely adopted for generating plausible views, videos, and

Lu Jiang, Di Xu, Qifan Xu, Arion Chatziioannou

Image-guided mouse irradiation is essential to understand interventions involving radiation prior to human studies. Our objective is to employ Swin UNEt Transformers (Swin UNETR) to segment native micro-CT and contrast-enhanced micro-CT scans and benchmark the results against 3D no-new-Net (nnU-Net). Swin UNETR reformulates mouse organ segmentation as a sequ

Cong Zhou, Jian Zhou

The intricate interplay between light and matter provides effective tools for manipulating topological phenomena. Here, we theoretically propose and computationally show that circularly polarized light hold the potential to transform the axion insulating phase into quantum anomalous Hall state in MnBi2Te4 thin films, featuring tunable Chern numbers (ranging

Yuta Tarumi, Keisuke Fukuda, Shin-ichi Maeda

State estimation for nonlinear state space models (SSMs) is a challenging task. Existing assimilation methodologies predominantly assume Gaussian posteriors on physical space, where true posteriors become inevitably non-Gaussian. We propose Deep Bayesian Filtering (DBF) for data assimilation on nonlinear SSMs. DBF constructs new latent variables $h_t$ in add

M. G. Delgadino, Bruno B. Suassuna, Rene Cabrera

We study quantitatively the overparametrization limit of the original Wasserstein-GAN algorithm. Effectively, we show that the algorithm is a stochastic discretization of a system of continuity equations for the parameter distributions of the generator and discriminator. We show that parameter clipping to satisfy the Lipschitz condition in the algorithm indu

Renyi Qu, Mark Yatskar

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from large language models (LLMs). This introduces randomness and compromises both transparency and reliability, which are esse

Hangzhi Guo, Firdaus Ahmed Choudhury, Tinghua Chen, Amulya Yadav

Counterfactual (CF) explanations for ML model predictions provide actionable recourse recommendations to individuals adversely impacted by predicted outcomes. However, despite being preferred by end-users, CF explanations have been shown to pose significant security risks in real-world applications; in particular, malicious adversaries can exploit CF explana

Kaveh Alimohammadi, Hao Wang, Ojas Gulati, Akash Srivastava

Existing differentially private (DP) synthetic data generation mechanisms typically assume a single-source table. In practice, data is often distributed across multiple tables with relationships across tables. In this paper, we introduce the first-of-its-kind algorithm that can be combined with any existing DP mechanisms to generate synthetic relational data

Vicky Zayats, Peter Chen, Melissa Ferrari, Dirk Padfield

Integrating multiple generative foundation models, especially those trained on different modalities, into something greater than the sum of its parts poses significant challenges. Two key hurdles are the availability of aligned data (concepts that contain similar meaning but is expressed differently in different modalities), and effectively leveraging unimod

Abderrahman Baza, Mohamed Rossafi, Choonkil Park

Using the direct method, we prove the generalised Hyers-Ulam stability of the following functional equation \begin{equation} \phi(x+y, z+w)+\phi(x-y, z-w)-2 \phi(x, z)-2 \phi(x, w)=0 \end{equation} in modular space satisfying the Fatou property or $\Delta_2$-condition.

Daozhi Shen, HeeBong Yang, Tarun Patel, Daniel A. Rhodes

A single photodetector with tunable detection wavelengths and polarization sensitivity can potentially be harnessed for diverse optical applications ranging from imaging and sensing to telecommunications. Such a device will require the combination of multiple material systems with different structures, bandgaps, and photoelectrical responses, which is extrem

Andreas Erlebach, Ghada Belhadj Hassine, Christian Thieme, Katrin Thieme

Materials that exhibit zero thermal expansion have numerous applications, ranging from everyday ceramic hobs to telescope mirrors to devices in optics and micromechanics. These materials include glass ceramics containing crystal phases with negative thermal expansion in at least one crystallographic direction, such as Ba1-xSrxZn2-2yMg2ySi2O7 solid solutions.

Yan Zhang

Before the era of fully automated vehicles, human is consistently an indispensable part of the driving system. Various studies have investigated drivers' cooperation with the vehicle under different conditions. In this article, we analyzed how non-driving-related tasks (NDRT) influence takeover time (TOT) by conducting a meta-analysis on 37 related papers. N

Xinhua Wu, Haoyu He, Yanchao Wang, Qi Wang

Ubiquitous mobile devices are generating vast amounts of location-based service data that reveal how individuals navigate and utilize urban spaces in detail. In this study, we utilize these extensive, unlabeled sequences of user trajectories to develop a foundation model for understanding urban space and human mobility. We introduce the \textbf{P}retrained \

Xiaobin Lin, Maoliang Wei, Kunhao Lei, Zijia Wang

On-chip structured light, with potentially infinite complexity, has emerged as a linchpin in the realm of integrated photonics. However, the realization of arbitrarily tailoring a multitude of light field dimensions in complex media remains a challenge1, Through associating physical light fields and mathematical function spaces by introducing a mapping opera

Guanglu Shi, Li Feng, Beili Ying, Shuting Li

Solar magnetic fields are closely related to various physical phenomena on the sun, which can be extrapolated with different models from photospheric magnetograms. However, the Open Flux Problem (OFP), the underestimation of the magnetic field derived from the extrapolated model, is still unsolved. To minimize the impact of the OFP, we propose three evaluati

Deng Pan, Nuno Moniz, Nitesh Chawla

The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations or rely on expert's knowledge of specific model structures that trade general applicability for efficiency. To address t

Andreas Erlebach, Christian Thieme, Carolin Müller, Stefan Hoffmann

Origin and composition dependence of the anisotropic thermomechanical properties are elucidated for Ba1-xSrxZn2Si2O7 (BZS) solid solutions. The high-temperature phase of BZS shows negative thermal expansion (NTE) along one crystallographic axis and highly anisotropic elastic properties characterized by X-ray diffraction experiments and simulations at the den

Paul Gagnon, Misha Benjamin, Justine Gauthier, Catherine Regis

Historically, open source commitments have been deemed irrevocable once materials are released under open source licenses. In this paper, the authors argue for the creation of a subset of rights that allows open source contributors to force users to (i) update to the most recent version of a model, (ii) accept new use case restrictions, or even (iii) cease u