May 2023 arXiv papers — page 30

Ben Moews

Modern mainstream financial theory is underpinned by the efficient market hypothesis, which posits the rapid incorporation of relevant information into asset pricing. Limited prior studies in the operational research literature have investigated tests designed for random number generators to check for these informational efficiencies. Treating binary daily r

Klaus Bongartz

We give a simplified complete proof for the classification of the selfinjective representation-finite algebras of finite dimension over an algebraically closed field. We explain the relations between the two different approaches and also to further developments. Many historical remarks are made.

Hao Geng, Deqing Wang, Fuzhen Zhuang, Xuehua Ming

Accurate citation count prediction of newly published papers could help editors and readers rapidly figure out the influential papers in the future. Though many approaches are proposed to predict a paper's future citation, most ignore the dynamic heterogeneous graph structure or node importance in academic networks. To cope with this problem, we propose a Dy

Asahi Ushio, Fernando Alva-Manchego, Jose Camacho-Collados

Generating questions along with associated answers from a text has applications in several domains, such as creating reading comprehension tests for students, or improving document search by providing auxiliary questions and answers based on the query. Training models for question and answer generation (QAG) is not straightforward due to the expected structu

Zhibin Lan, Jiawei Yu, Xiang Li, Wen Zhang

Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a casca

Quan Quan, Runxiao Liu, Hao Liu, Zeqing Ma

With the high focus on autonomous aerial refueling recently, it becomes increasingly urgent to design efficient methods or algorithms to solve AAR problems in complicated aerial environments. Apart from the complex aerodynamic disturbance, another problem is the pose estimation error caused by the camera calibration error, installation error, or 3D object mo

J. W. van Holten

This paper reviews the dynamics of an isotropic and homogeneous cosmological scalar field. A general approach to the solution of the Einstein-Klein-Gordon equations is developed, which does not require slow-roll or other approximations. General conclusions about the qualitative behaviour of the solutions can be drawn, and examples of explicit solutions for s

Laxman Prasad Goswami, Amita Das, Anuj Vijay

Recent advancements in low-frequency short-pulse $CO_2$ lasers and the production of strong magnetic fields have made experimental studies on laser interactions with magnetized plasma a near-future possibility. Therefore, theoretical and numerical simulation studies have been pursued lately in this direction [A. Das, Review of Modern Plasma Physics 4, 1 (202

Yiqian Chen, Peng Wang, Houwen Wu, Haitang Yang

We examine the gravitational lensing phenomenon caused by photon spheres in the Born-Infeld naked singularity spacetime, where gravity is coupled with Born-Infeld electrodynamics. Specifically, our focus lies on relativistic images originating from a point-like light source generated by strong gravitational lensing near photon spheres, as well as images of a

Dongxiang Yan, Tongxin Li, Changhong Zhao, Han Wang

The wide deployment of distributed renewable energy sources and electric vehicles can help mitigate climate crisis. This necessitates new business models in the power sector to hedge against uncertainties while imposing a strong coupling between the connected power and transportation networks. To address these challenges, this paper first proposes an energy

Omkar Ranadive, Nikhil Thakurdesai, Ari S Morcos, Matthew Leavitt

It is commonly observed that deep networks trained for classification exhibit class-selective neurons in their early and intermediate layers. Intriguingly, recent studies have shown that these class-selective neurons can be ablated without deteriorating network function. But if class-selective neurons are not necessary, why do they exist? We attempt to answe

Yangjie Zhou, Yaoxu Song, Jingwen Leng, Zihan Liu

Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features. As such, achieving high-performance execution for GNNs becomes crucially important. Prior works have proposed to explore the sparsity (i.e., low density) in the input graph to accelerate GNNs, which uses the full-graph-level or block-level sparsity

S Venkatesh Kumaran, Dariusz Garbiec, José Manuel Torralba

A novel approach to developing high entropy alloys (HEAs) using spark plasma sintering (SPS) was explored in this work where a mix of commercial commodity powders like Ni625, CoCrF75, and 316L was used instead of pre-alloyed powders avoiding the expensive pre-alloying steps like mechanical alloying or gas atomizing. Three non-equiatomic HEAs, based on Co, Cr

Atnafu Lambebo Tonja, Hellina Hailu Nigatu, Olga Kolesnikova, Grigori Sidorov

This paper describes CIC NLP's submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas. We present the system descriptions for three methods. We used two multilingual models, namely M2M-100 and mBART50, and one bilingual (one-to-one) -- Helsinki NLP Spanish-English translation model, and experime

Ankita Sengupta, Basudev Nag Chowdhury, Bodhishatwa Roy, Biswarup Satpati

The current work proposes a novel scheme for developing a light-activated non-filamentary memristor device by fabricating an Au-nanoparticle embedded HfO$_2$-bilayer/p-Si MOS structure. Under illumination, the electrons in such embedded Au-nanoparticles are excited from d-level to quantized s-p level and are swept out on application of an appropriate gate bi

William Bains, Matthew A. Pasek, Sukrit Ranjan, Janusz J. Petkowski

Phosphorus (III) oxide (P$_4$O$_6$) has been suggested to be a major component of the gas phase phosphorus chemistry in the atmospheres of gas giant planets and of Venus. However, P$_4$O$_6$'s proposed role is based on thermodynamic modeling, itself based on values for the free energy of formation of P$_4$O$_6$ estimated from limited experimental data. Value

Atnafu Lambebo Tonja, Christian Maldonado-Sifuentes, David Alejandro Mendoza Castillo, Olga Kolesnikova

In this paper, we present a parallel Spanish-Mazatec and Spanish-Mixtec corpus for machine translation (MT) tasks, where Mazatec and Mixtec are two indigenous Mexican languages. We evaluated the usability of the collected corpus using three different approaches: transformer, transfer learning, and fine-tuning pre-trained multilingual MT models. Fine-tuning t

Osman Berke Guney, Deniz Kucukahmetler, Huseyin Ozkan

Objective: SSVEP-based BCI spellers assist individuals experiencing speech difficulties by enabling them to communicate at a fast rate. However, achieving a high information transfer rate (ITR) in most prominent methods requires an extensive calibration period before using the system, leading to discomfort for new users. We address this issue by proposing a

Simina Brânzei, Mahsa Derakhshan, Negin Golrezaei, Yanjun Han

We consider repeated multi-unit auctions with uniform pricing, which are widely used in practice for allocating goods such as carbon licenses. In each round, $K$ identical units of a good are sold to a group of buyers that have valuations with diminishing marginal returns. The buyers submit bids for the units, and then a price $p$ is set per unit so that all

Jinghong Li, Koichi Ota, Wen Gu, Shinobu Hasegawa

With the widespread use of the internet, it has become increasingly crucial to extract specific information from vast amounts of academic articles efficiently. Data mining techniques are generally employed to solve this issue. However, data mining for academic articles is challenging since it requires automatically extracting specific patterns in complex and

Xiao Hu, Jianxiong Li, Xianyuan Zhan, Qing-Shan Jia

Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents' behavior with human desired outcomes, but is often restrained by costly human feedback. To improve feedback efficiency, most existing PbRL methods focus on selecting queries to maximally improve the overall quality of the reward model, but counter-intuitively, we find t

Amit Kumar, Mani Shankar Pandey, Sumit Kumar Upadhyay

This paper aims to introduce the concept of nilpotency and capability in multiplicative Lie algebras. Also, we see the existence of covers of a multiplicative Lie algebra and thoroughly examine their relationships with capable and perfect multiplicative Lie algebras.

Mohammad Asif, Diya Srivastava, Aditya Gupta, Uma Shanker Tiwary

Inter-subject or subject-independent emotion recognition has been a challenging task in affective computing. This work is about an easy-to-implement emotion recognition model that classifies emotions from EEG signals subject independently. It is based on the famous EEGNet architecture, which is used in EEG-related BCIs. We used the Dataset on Emotion using N

Yuan Liu, Peng Wang, Cheng Lin, Xiaoxiao Long

We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment. Multiview reconstruction of reflective objects is extremely challenging because specular reflections are view-dependent and thus violate the multiview consistency, which is the cor

Gonzalo Maximiliano Lopez, Juan Pablo Aparicio

In the modeling of parasite transmission dynamics, understanding the reproductive characteristics of these parasites is crucial. This paper presents a mathematical model that explores the reproductive behavior of dioecious parasites and its impact on transmission dynamics. Specifically, the study focuses on the investigation of various reproductive variables

Shuyu Guo, Shuo Zhang, Weiwei Sun, Pengjie Ren

Explanations in conventional recommender systems have demonstrated benefits in helping the user understand the rationality of the recommendations and improving the system's efficiency, transparency, and trustworthiness. In the conversational environment, multiple contextualized explanations need to be generated, which poses further challenges for explanation

Masahiro Asada, Safumi Suzuki

The frequency dependence of negative differential conductance (NDC) is an important property for the resonant-tunneling-diode terahertz source. Among several phenomena determining the frequency dependence, this paper shows that the effect of potential change of the quantum well due to electron charge can be analyzed with a simple and tractable model based on

Subhendu Das, Sridhar Tripathy, Jaydeep Datta, Nayana Majumdar

Muon scattering tomography is a non-destructive imaging technique that utilizes the penetrating properties and multiple Coulomb scattering of muons to produce detailed internal images of objects. This information is crucial for various applications, including material identification, civil structure investigation, geological surveys, archaeological investiga

Jungwoo Heo, Chan-yeong Lim, Ju-ho Kim, Hyun-seo Shin

The application of speech self-supervised learning (SSL) models has achieved remarkable performance in speaker verification (SV). However, there is a computational cost hurdle in employing them, which makes development and deployment difficult. Several studies have simply compressed SSL models through knowledge distillation (KD) without considering the targe

Pedro Faustini, Zhiyu Chen, Besnik Fetahu, Oleg Rokhlenko

Spoken Question Answering (QA) is a key feature of voice assistants, usually backed by multiple QA systems. Users ask questions via spontaneous speech which can contain disfluencies, errors, and informal syntax or phrasing. This is a major challenge in QA, causing unanswered questions or irrelevant answers, and leading to bad user experiences. We analyze fai

Aymen Laadhari, Ahmad Deeb

In this work, we propose a numerical approach for simulations of large deformations of interfaces in a level set framework. To obtain a fast and viable numerical solution in both time and space, temporal discretization is based on the composition of one-step methods exhibiting higher orders and stability, especially in the case of stiff problems with strongl

Hai-Yang Jin, Zhi-An Wang, Leyun Wu

This paper is concerned with the global boundedness and stability of classical solutions to an alarm-taxis system describing the burglar alarm hypothesis as an important mechanism of anti-predation behavior when species are threaten by predators. Compared to the existing prey-taxis systems, the alarm-taxis system has more complicated coupling structure and a

Bill Yuchen Lin, Yicheng Fu, Karina Yang, Faeze Brahman

We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and prompting large language models (LLMs) to enhance task completion performance. The framework comprises two primary modu

K. J. Kevin Feng, Maxwell James Coppock, David W. McDonald

UX practitioners (UXPs) face novel challenges when working with and communicating artificial intelligence (AI) as a design material. We explore how UXPs communicate AI concepts when given hands-on experience training and experimenting with AI models. To do so, we conducted a task-based design study with 27 UXPs in which they prototyped and created a design p

Jaewoo Ahn, Yeda Song, Sangdoo Yun, Gunhee Kim

In order to build self-consistent personalized dialogue agents, previous research has mostly focused on textual persona that delivers personal facts or personalities. However, to fully describe the multi-faceted nature of persona, image modality can help better reveal the speaker's personal characteristics and experiences in episodic memory (Rubin et al., 20

Ehsan Saleh, Saba Ghaffari, Timothy Bretl, Luke Olson

This work proposes a solution for the problem of training physics-informed networks under partial integro-differential equations. These equations require an infinite or a large number of neural evaluations to construct a single residual for training. As a result, accurate evaluation may be impractical, and we show that naive approximations at replacing these

Kaize Ding, Albert Jiongqian Liang, Bryan Perrozi, Ting Chen

Learning expressive representations for high-dimensional yet sparse features has been a longstanding problem in information retrieval. Though recent deep learning methods can partially solve the problem, they often fail to handle the numerous sparse features, particularly those tail feature values with infrequent occurrences in the training data. Worse still

Davide Bilò, Luciano Gualà, Stefano Leucci, Luca Pepè Sciarria

In the \emph{$k$-Diameter-Optimally Augmenting Tree Problem} we are given a tree $T$ of $n$ vertices as input. The tree is embedded in an unknown \emph{metric} space and we have unlimited access to an oracle that, given two distinct vertices $u$ and $v$ of $T$, can answer queries reporting the cost of the edge $(u,v)$ in constant time. We want to augment $T$

Zhuo Li, Huangzhao Zhang, Zhi Jin, Ge Li

Bug localization, which is used to help programmers identify the location of bugs in source code, is an essential task in software development. Researchers have already made efforts to harness the powerful deep learning (DL) techniques to automate it. However, training bug localization model is usually challenging because it requires a large quantity of data

Woocheol Choi

In this work, we establish convergence results for the distributed proximal point algorithm (DPPA) for distributed optimization problems. We consider the problem on the whole domain Rd and find a general condition on the stepsize and cost functions such that the DPPA is stable. We prove that the DPPA with stepsize $\eta > 0$ exponentially converges to an $O(

Xuhai Chen, Yue Han, Jiangning Zhang

In this technical report, we briefly introduce our solution for the Zero/Few-shot Track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. For industrial visual inspection, building a single model that can be rapidly adapted to numerous categories without or with only a few normal reference images is a promising research direction. This is pr

T. Shang, J. Z. Zhao, Lun-Hui Hu, D. J. Gawryluk

We report a study of the noncentrosymmetric TaReSi superconductor by means of muon-spin rotation and relaxation ($\mu$SR) technique, complemented by electronic band-structure calculations. Its superconductivity, with $T_c$ = 5.5 K and upper critical field $\mu_0H_\mathrm{c2}(0)$ $\sim$ 3.4 T, was characterized via electrical-resistivity- and magnetic-suscept

Tiancheng Jin, Junyan Liu, Chloé Rouyer, William Chang

Existing online learning algorithms for adversarial Markov Decision Processes achieve ${O}(\sqrt{T})$ regret after $T$ rounds of interactions even if the loss functions are chosen arbitrarily by an adversary, with the caveat that the transition function has to be fixed. This is because it has been shown that adversarial transition functions make no-regret le

Sanjay Dharmavaram, Basant Lal Sharma

We revisit the notion of parametrization invariance while introducing certain weakened notions of invariance in the calculus of variations. In this work, we employ a straightforward approach in the classical setting and mostly restrict attention to functionals on one-dimensional domains. We establish a connection between parametrization invariant functionals

Daking Rai, Bailin Wang, Yilun Zhou, Ziyu Yao

Compositional and domain generalization present significant challenges in semantic parsing, even for state-of-the-art semantic parsers based on pre-trained language models (LMs). In this study, we empirically investigate improving an LM's generalization in semantic parsing with two simple techniques: at the token level, we introduce a token preprocessing met

Haoxiang Luo, Jin Zhang, Xinling Li, Zonghang Li

Decentralized, tamper-proof blockchain is regarded as a solution to a challenging authentication issue in the Internet of Vehicles (IoVs). However, the consensus time and communication overhead of blockchain increase significantly as the number of vehicles connected to the blockchain. To address this issue, vehicular fog computing has been introduced to impr

Kai Wu, Yujian Betterest Li, Jian Lou, Xiaoyu Zhang

In the realm of daily services, the deployment of deep neural networks underscores the paramount importance of their reliability. However, the vulnerability of these networks to adversarial attacks, primarily evasion-based, poses a concerning threat to their functionality. Common methods for enhancing robustness involve heavy adversarial training or leveragi

Hui Li, Yongbiao Xiao, Chunyang Cheng, Zhongwei Shen

Infrared and visible image fusion aims to generate synthetic images simultaneously containing salient features and rich texture details, which can be used to boost downstream tasks. However, existing fusion methods are suffering from the issues of texture loss and edge information deficiency, which result in suboptimal fusion results. Meanwhile, the straight

Dianbo Liu, Samuele Bolotta, He Zhu, Yoshua Bengio

Attention has become a common ingredient in deep learning architectures. It adds a dynamical selection of information on top of the static selection of information supported by weights. In the same way, we can imagine a higher-order informational filter built on top of attention: an Attention Schema (AS), namely, a descriptive and predictive model of attenti

Kaiwen Xu, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma

A concept-based classifier can explain the decision process of a deep learning model by human-understandable concepts in image classification problems. However, sometimes concept-based explanations may cause false positives, which misregards unrelated concepts as important for the prediction task. Our goal is to find the statistically significant concept for

Yongbiao Xiao, Hui Li, Chunyang Cheng, Xiaoning Song

Infrared and visible image fusion task aims to generate a fused image which contains salient features and rich texture details from multi-source images. However, under complex illumination conditions, few algorithms pay attention to the edge information of local regions which is crucial for downstream tasks. To this end, we propose a fusion network based on

Zhenrui Yue, Huimin Zeng, Mengfei Lan, Heng Ji

With emerging online topics as a source for numerous new events, detecting unseen / rare event types presents an elusive challenge for existing event detection methods, where only limited data access is provided for training. To address the data scarcity problem in event detection, we propose MetaEvent, a meta learning-based framework for zero- and few-shot

Jueming Hu, Jean-Raphael Gaglione, Yanze Wang, Zhe Xu

We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q-learning with reward machines for stochastic games (QRM-SG), to learn the best-response strategy at Nash equi

Vahid Reza Nafisi, Roshanak Ghods

Persian Medicine (PM) uses wrist temperature/humidity and pulse to determine a person's health status and temperament. However, the diagnosis may depend on the physician's interpretation, hindering the combination of PM with modern medical methods. This study proposes a system for measuring pulse signals and temperament detection based on PM. The system uses

Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang

Dense retrieval is widely used for entity linking to retrieve entities from large-scale knowledge bases. Mainstream techniques are based on a dual-encoder framework, which encodes mentions and entities independently and calculates their relevances via rough interaction metrics, resulting in difficulty in explicitly modeling multiple mention-relevant parts wi

Neel Kanwal, Trygve Eftestol, Farbod Khoraminia, Tahlita CM Zuiverloon

Computational Pathology (CPATH) systems have the potential to automate diagnostic tasks. However, the artifacts on the digitized histological glass slides, known as Whole Slide Images (WSIs), may hamper the overall performance of CPATH systems. Deep Learning (DL) models such as Vision Transformers (ViTs) may detect and exclude artifacts before running the di

Rui Cao, Jing Jiang

Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA). Our approach is motivated by a few observations. First, VQA questions often require multiple steps of reasoning, which is still a capability that most PTMs lack. Second, different steps in VQA re

Minghao Fu, Ke Zhu, Jianxin Wu

In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to real-world applications, this paper proposes a practical FSL (pFSL) setting. pFSL is based on unsupervised pretrained models (analogous to human prior knowledge) and recognizes many novel classes simultaneously. Compared to traditional FSL, pFSL is simpler in its for

Yongyu Mu, Abudurexiti Reheman, Zhiquan Cao, Yuchun Fan

Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large language models (LLMs) with TMs and making them better translators. We find that the ability of LLMs to ``understand'' prompts is indeed helpful for making better use of TMs. Experiment

Yinpeng Hu, Yi Sun, Ye Lu, Huan Li

The continuous push for high-performance photonic switches is one of the most crucial premises for the sustainable scaling of programmable and reconfigurable photonic circuits for a wide spectrum of applications. Conventional optical switches rely on the perturbative mechanisms of mode coupling or mode interference, resulting in inherent bottlenecks in their

Xiao Fang, Yuta Koike, Song-Hao Liu, Yi-Kun Zhao

In the literature of high-dimensional central limit theorems, there is a gap between results for general limiting correlation matrix $\Sigma$ and the strongly non-degenerate case. For the general case where $\Sigma$ may be degenerate, under certain light-tail conditions, when approximating a normalized sum of $n$ independent random vectors by the Gaussian di

Asma Ben Abacha, Wen-wai Yim, George Michalopoulos, Thomas Lin

Recent studies on automatic note generation have shown that doctors can save significant amounts of time when using automatic clinical note generation (Knoll et al., 2022). Summarization models have been used for this task to generate clinical notes as summaries of doctor-patient conversations (Krishna et al., 2021; Cai et al., 2022). However, assessing whic

Shanshan Chen, Yihuan Sun

In this paper, we consider a coupled Brusselator model of chemical reactions, for which no symmetry for the coupling matrices is assumed. We show that the model can undergoes a Hopf bifurcation, and consequently periodic solutions can arise when the dispersal rates are large. Moreover, the effect of the coupling matrices on the Hopf bifurcation value is cons

Fayez Abu-Ajamieh, Marco Frasca, Sudhir K. Vempati

Di-Higgs couplings to fermions of the form $h^{2}\overline{f}f$ are absent in the Standard Model, however, they are present in several physics Beyond Standard Model (BSM) extensions, including those with vector-like fermions. In Effective Field Theories (EFTs), such as the Standard Model Effective Field Theory (SMEFT) and the Higgs Effective Field Theory (HE

Qichen Huang, Biwei Jiang, Dingshan Deng, Bin Yu

Radio observation is crucial to understanding the wind mechanism of OB stars but very scarce. This work estimates the flux at 1450MHz ($S_{\rm 1.4GHz}$) of about 5,000 OB stars identified by the LAMOST spectroscopic survey and confirmed by the Gaia astrometric as well as astrophysical measurements. The calculation is performed under the free-free emission me

Ming Chen, Jie Han, Yantao Tang, Donglei Yang

We prove that for $r\in \mathbb{N}$ with $r\geq 2$ and $\mu>0$, there exist $\alpha>0$ and $n_{0}$ such that for every $n\geq n_{0}$, every $n$-vertex graph $G$ with $\delta(G)\geq \left(1-\frac{1}{r}+\mu\right)n$ and $\alpha(G)\leq \alpha n$ contains an $r$-th power of a Hamilton cycle. We also show that the minimum degree condition is asymptotically sharp

Haoxiang Yu, Jingyi An, Evan King, Edison Thomaz

Understanding the complexity of human activities solely through an individual's data can be challenging. However, in many situations, surrounding individuals are likely performing similar activities, while existing human activity recognition approaches focus almost exclusively on individual measurements and largely ignore the context of the activity. Conside

Xianjun Yang, Wei Cheng, Yue Wu, Linda Petzold

Large language models (LLMs) have notably enhanced the fluency and diversity of machine-generated text. However, this progress also presents a significant challenge in detecting the origin of a given text, and current research on detection methods lags behind the rapid evolution of LLMs. Conventional training-based methods have limitations in flexibility, pa

Yiqian Wang, Alexandra Warter, Melina Cavichini, Varsha Alex

Optical Coherence Tomography (OCT) is one of the most important retinal imaging technique. However, involuntary motion artifacts still pose a major challenge in OCT imaging that compromises the quality of downstream analysis, such as retinal layer segmentation and OCT Angiography. We propose deep learning based neural networks to correct axial and coronal mo

Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun

Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation and low latency. In this paper, we investigate the potential of connectionist temporal classification (CTC) for non-autoregressive speech translation (NAST). In particular, we devel

Jun-Shuai Wang, Yong-Liang Ma

The roles of the lightest vector mesons $\rho$ and $\omega$ in the multi-skyrmion states are studied using the hidden local symmetry approach upto the next to leading order including the homogeneous Wess-Zumino terms. The low energy constants in the effective field theory are determined by using the Sakai-Sugimoto model and the flat-space five-dimensional Ya

Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose \textit{Progressive Down-Sampling} (PDS) which gradually compresses the acoustic features into coarser-grained units containing

Feiyu Li, Jun Yang

Image inverse halftoning is a classic image restoration task, aiming to recover continuous-tone images from halftone images with only bilevel pixels. Because the halftone images lose much of the original image content, inverse halftoning is a classic ill-problem. Although existing inverse halftoning algorithms achieve good performance, their results lose ima

Matthias Kramer, Daniel Valero

High Froude-number flows become self-aerated when the destabilizing effect of turbulence overcomes gravity and surface tension forces. Traditionally, the resulting air concentration profile has been explained using single-layer approaches that invoke solutions of the advection-diffusion equation for air in water, i.e., bubbles' dispersion. Based on a wide ra

Huixue Zhou, Robin Austin, Sheng-Chieh Lu, Greg Silverman

Objective: Our study aimed to construct an exhaustive Complementary and Integrative Health (CIH) Lexicon (CIHLex) to better represent the often underrepresented physical and psychological CIH approaches in standard terminologies. We also intended to apply advanced Natural Language Processing (NLP) models such as Bidirectional Encoder Representations from Tra

Yihe Zhou, Shunyu Liu, Yunpeng Qing, Kaixuan Chen

Centralized Training with Decentralized Execution (CTDE) has recently emerged as a popular framework for cooperative Multi-Agent Reinforcement Learning (MARL), where agents can use additional global state information to guide training in a centralized way and make their own decisions only based on decentralized local policies. Despite the encouraging results

Jinpeng Zhang, Nini Xiao, Ke Wang, Chuanqi Dong

Lexically constrained neural machine translation (LCNMT), which controls the translation generation with pre-specified constraints, is important in many practical applications. Current approaches to LCNMT typically assume that the pre-specified lexical constraints are contextually appropriate. This assumption limits their application to real-world scenarios

Corbyn Terpstra, Ibrahim Khebour, Mariah Bradford, Brett Wisniewski

Collaborative problem solving (CPS) in teams is tightly coupled with the creation of shared meaning between participants in a situated, collaborative task. In this work, we assess the quality of different utterance segmentation techniques as an aid in annotating CPS. We (1) manually transcribe utterances in a dataset of triads collaboratively solving a probl

Christos Sakaridis, David Bruggemann, Fisher Yu, Luc Van Gool

Adaptation of semantic segmentation networks to different visual conditions is vital for robust perception in autonomous cars and robots. However, previous work has shown that most feature-level adaptation methods, which employ adversarial training and are validated on synthetic-to-real adaptation, provide marginal gains in condition-level adaptation, being

Gabe Murray, Jeff Field, Patrick Stockton, Ali Pezeshki

Imaging beyond the diffraction limit barrier has attracted wide attention due to the ability to resolve image features that were previously hidden. Of the various super-resolution microscopy techniques available, a particularly simple method called saturated excitation microscopy (SAX) requires only a simple modification of a laser scanning microscope where

Brett Reynolds, Nathan Schneider, Aryaman Arora

CGELBank is a treebank and associated tools based on a syntactic formalism for English derived from the Cambridge Grammar of the English Language (CGEL; Huddleston and Pullum, 2002). It is hosted on GitHub at https://github.com/nert-nlp/cgel. This document lays out the particularities of the CGELBank annotation scheme.

Yuhang Li, Abhishek Moitra, Tamar Geller, Priyadarshini Panda

Spiking Neural Networks (SNNs) have recently attracted widespread research interest as an efficient alternative to traditional Artificial Neural Networks (ANNs) because of their capability to process sparse and binary spike information and avoid expensive multiplication operations. Although the efficiency of SNNs can be realized on the In-Memory Computing (I

Quang-Nam Nguyen, Nicholas Adrian, Quang-Cuong Pham

Mobile manipulators have gained attention for the potential in performing large-scale tasks which are beyond the reach of fixed-base manipulators. The Robotic Task Sequencing Problem for mobile manipulators often requires optimizing the motion sequence of the robot to visit multiple targets while reducing the number of base placements. A two-step approach to

Div Bhagia

This paper presents a novel approach to distinguish the impact of duration-dependent forces and adverse selection on the exit rate from unemployment by leveraging variation in the length of layoff notices. I formulate a Mixed Hazard model in discrete time and specify the conditions under which variation in notice length enables the identification of structur

Yung-Hsuan Lai, Yen-Chun Chen, Yu-Chiang Frank Wang

Audio-visual learning has been a major pillar of multi-modal machine learning, where the community mostly focused on its modality-aligned setting, i.e., the audio and visual modality are both assumed to signal the prediction target. With the Look, Listen, and Parse dataset (LLP), we investigate the under-explored unaligned setting, where the goal is to recog

Xiangyu Liu, Souradip Chakraborty, Yanchao Sun, Furong Huang

Most existing works focus on direct perturbations to the victim's state/action or the underlying transition dynamics to demonstrate the vulnerability of reinforcement learning agents to adversarial attacks. However, such direct manipulations may not be always realizable. In this paper, we consider a multi-agent setting where a well-trained victim agent $\nu$

Xirong Ma

Principal Component Analysis (PCA) is a pivotal technique widely utilized in the realms of machine learning and data analysis. It aims to reduce the dimensionality of a dataset while minimizing the loss of information. In recent years, there have been endeavors to utilize homomorphic encryption in privacy-preserving PCA algorithms for the secure cloud comput

Hui Ouyang

We proposed an iterate scheme for solving convex-concave saddle-point problems associated with general convex-concave functions. We demonstrated that when our iterate scheme is applied to a special class of convex-concave functions, which are constructed by a bilinear coupling term plus a difference of two convex functions, it becomes a generalization of sev

Martin Saveski, Steven Jecmen, Nihar B. Shah, Johan Ugander

Peer review assignment algorithms aim to match research papers to suitable expert reviewers, working to maximize the quality of the resulting reviews. A key challenge in designing effective assignment policies is evaluating how changes to the assignment algorithm map to changes in review quality. In this work, we leverage recently proposed policies that intr

Md Abulkalam Azad, Ahmed Mohammed, Maryna Waszak, Brian Elvesæter

Today ship hull inspection including the examination of the external coating, detection of defects, and other types of external degradation such as corrosion and marine growth is conducted underwater by means of Remotely Operated Vehicles (ROVs). The inspection process consists of a manual video analysis which is a time-consuming and labor-intensive process.

Sijia Wang, Alexander Hanbo Li, Henry Zhu, Sheng Zhang

Entities can be expressed in diverse formats, such as texts, images, or column names and cell values in tables. While existing entity linking (EL) models work well on per modality configuration, such as text-only EL, visual grounding, or schema linking, it is more challenging to design a unified model for diverse modality configurations. To bring various mod

Matt Menickelly

We present a technique for model-based derivative-free optimization called \emph{basis sketching}. Basis sketching consists of taking random sketches of the Vandermonde matrix employed in constructing an interpolation model. This randomization enables weakening the general requirement in model-based derivative-free methods that interpolation sets contain a f

Chen Hu, Mit H. Naik, Yang-Hao Chan, Steven G. Louie

Optical dynamics in van der Waals heterobilayers is of fundamental scientific and practical interest. Based on a time-dependent adiabatic GW approach, we discover a new many-electron (excitonic) channel for converting photoexcited intralayer to interlayer excitations and the associated ultrafast optical responses in heterobilayers, which is conceptually diff

Allan Sly, Youngtak Sohn

The local behavior of typical solutions of random constraint satisfaction problems (CSP) describes many important phenomena including clustering thresholds, decay of correlations, and the behavior of message passing algorithms. When the constraint density is low, studying the planted model is a powerful technique for determining this local behavior which in

Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian

Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a prohibitively large amount of memory. Zeroth-order (ZO) methods can in principle estimate gradients using only two forward passes but are theorized to be catastrophically slow for optimizing large models. In this work, we pro

Daiwei Chen, Wei-Kai Chang, Pratik Chaudhari

We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning capacity'' which is a measure of the effective dimensionality of a model. We show that the learning capacity is a useful notion of the complexity because (a) it correlates well wi

Zichun Yu, Chenyan Xiong, Shi Yu, Zhiyuan Liu

Retrieval augmentation can aid language models (LMs) in knowledge-intensive tasks by supplying them with external information. Prior works on retrieval augmentation usually jointly fine-tune the retriever and the LM, making them closely coupled. In this paper, we explore the scheme of generic retrieval plug-in: the retriever is to assist target LMs that may

Zhengbang Zhu, Minghuan Liu, Liyuan Mao, Bingyi Kang

Offline reinforcement learning (RL) aims to learn policies from pre-existing datasets without further interactions, making it a challenging task. Q-learning algorithms struggle with extrapolation errors in offline settings, while supervised learning methods are constrained by model expressiveness. Recently, diffusion models (DMs) have shown promise in overco

Takeshi Suzuki, Yuya Kubota, Natsuki Mitsuishi, Shunsuke Akatsuka

Optical control of crystal structures is a promising route to change physical properties including topological nature of a targeting material. Time-resolved X-ray diffraction measurements using the X-ray free-electron laser are performed to study the ultrafast lattice dynamics of VTe$_2$, which shows a unique charge-density-wave (CDW) ordering coupled to the

Hongjie Wang, Bhishma Dedhia, Niraj K. Jha

Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence. Token pruning is an emerging solution to address this challenge due to its ease of deployment on various Transformer backbones. However, most token pru