May 2023 arXiv papers — page 38

Anastasia A. Molodtsova, Mikhail K. Buzakov, Oleg I. Burmistrov, Alina D. Rozenblit

Active matter composed of self-propelled particles features fascinating self-organization phenomena, spanning from motility-induced phase separation to phototaxis to topological excitations depending on the nature and parameters of the system. In the present paper, we consider micelle formation by active particles with a broken symmetry having a circular bac

Liam Walsh, Mengbin Ye, Brian D. O. Anderson, Zhiyong Sun

This paper considers the classical Susceptible--Infected--Susceptible (SIS) network epidemic model, which describes a disease spreading through $n$ nodes, with the network links governing the possible transmission pathways of the disease between nodes. We consider feedback control to eliminate the disease in scenarios where the disease would otherwise persis

Gianfranco Cortes, Yue Yu, Robin Chen, Melissa Armstrong

With the advent of group equivariant convolutions in deep networks literature, spherical CNNs with $\mathsf{SO}(3)$-equivariant layers have been developed to cope with data that are samples of signals on the sphere $S^2$. One can implicitly obtain $\mathsf{SO}(3)$-equivariant convolutions on $S^2$ with significant efficiency gains by explicitly requiring gau

Tomoki Inoue, Koyo Kubota, Tsubasa Ikami, Yasuhiro Egami

Time-series clustering serves as a powerful data mining technique for time-series data in the absence of prior knowledge about clusters. A large amount of time-series data with large size has been acquired and used in various research fields. Hence, clustering method with low computational cost is required. Given that a quantum-inspired computing technology,

O. Adriani, Y. Akaike, K. Asano, Y. Asaoka

We present the observation of a charge-sign dependent solar modulation of galactic cosmic rays (GCRs) with the CALorimetric Electron Telescope onboard the International Space Station over 6 yr, corresponding to the positive polarity of the solar magnetic field. The observed variation of proton count rate is consistent with the neutron monitor count rate, val

Amanda Folsom, Joshua Males, Larry Rolen, Matthias Storzer

In 1986, Andrews studied the function $\sigma(q)$ from Ramanujan's ``Lost" Notebook, and made several conjectures on its Fourier coefficients $S(n)$, which count certain partition ranks. In 1988, Andrews-Dyson-Hickerson famously resolved these conjectures, relating the coefficients $S(n)$ to the arithmetic of $\mathbb Q(\sqrt{6})$; this relationship was furt

Haotian Sun, Yuchen Zhuang, Lingkai Kong, Bo Dai

Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans that are not adaptable to environmental feedback. Consequently, the sequential decision-making performance of LLM agents

WeiLai Xiang, FengQi Liu, Dan Li, ZhaoNan Tan

We propose a novel ray reordering technique to accelerate the ray tracing process by encoding and sorting rays prior to traversal. Instead of spatial coordinates, our method encodes rays according to the cuts of the hierarchical acceleration structure, which is called the hierarchy cut code. This approach can better adapt to the acceleration structure and ob

Will Held, Caleb Ziems, Diyi Yang

Large Language Models, the dominant starting point for Natural Language Processing (NLP) applications, fail at a higher rate for speakers of English dialects other than Standard American English (SAE). Prior work addresses this using task-specific data or synthetic data augmentation, both of which require intervention for each dialect and task pair. This pos

Tony Zheng, Monimoy Bujarbaruah, Francesco Borrelli

We present a data-driven optimization approach for robotic controlled deposition with a degradable tool. Existing methods make the assumption that the tool tip is not changing or is replaced frequently. Errors can accumulate over time as the tool wears away and this leads to poor performance in the case where the tool degradation is unaccounted for during de

Zhe Huang, Yudian Li

Most generic object detectors are mainly built for standard object detection tasks such as COCO and PASCAL VOC. They might not work well and/or efficiently on tasks of other domains consisting of images that are visually different from standard datasets. To this end, many advances have been focused on adapting a general-purposed object detector with limited

Kent K. Chang, Danica Chen, David Bamman

We present a new dataset for studying conversation disentanglement in movies and TV series. While previous work has focused on conversation disentanglement in IRC chatroom dialogues, movies and TV shows provide a space for studying complex pragmatic patterns of floor and topic change in face-to-face multi-party interactions. In this work, we draw on theoreti

Julian Büchel, Athanasios Vasilopoulos, Benedikt Kersting, Frederic Odermatt

The precise programming of crossbar arrays of unit-cells is crucial for obtaining high matrix-vector-multiplication (MVM) accuracy in analog in-memory computing (AIMC) cores. We propose a radically different approach based on directly minimizing the MVM error using gradient descent with synthetic random input data. Our method significantly reduces the MVM er

Xiaoming Shi, Siqiao Xue, Kangrui Wang, Fan Zhou

Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and help improve the prediction performance of event sequence models. We design LAMP, a framework that integrates a large language model in event prediction. Particularly, the language mo

Jianyang Gu, Kai Wang, Wei Jiang, Yang You

Replay-based methods have proved their effectiveness on online continual learning by rehearsing past samples from an auxiliary memory. With many efforts made on improving training schemes based on the memory, however, the information carried by each sample in the memory remains under-investigated. Under circumstances with restricted storage space, the inform

Weng-Long Chang, Renata Wong, Wen-Yu Chung, Yu-Hao Chen

Given an undirected, unweighted graph with $n$ vertices and $m$ edges, the maximum cut problem is to find a partition of the $n$ vertices into disjoint subsets $V_1$ and $V_2$ such that the number of edges between them is as large as possible. Classically, it is an NP-complete problem, which has potential applications ranging from circuit layout design, stat

Jokin Labaien, Tsuyoshi Idé, Pin-Yu Chen, Ekhi Zugasti

This paper addresses the task of anomaly diagnosis when the underlying data generation process has a complex spatio-temporal (ST) dependency. The key technical challenge is to extract actionable insights from the dependency tensor characterizing high-order interactions among temporal and spatial indices. We formalize the problem as supervised dependency disc

Anu Kumari

The detection and classification of entanglement properties in a two-qubit and a multi-qubit system is a topic of great interest. This topic has been extensively studied, and as a result, we discovered various approaches for detecting and classifying multi-qubit, in particular three-qubit entangled states. The emphasis of this work is on a formalism of metho

Navid Mohammadi Foumani, Chang Wei Tan, Geoffrey I. Webb, Mahsa Salehi

Transformers have demonstrated outstanding performance in many applications of deep learning. When applied to time series data, transformers require effective position encoding to capture the ordering of the time series data. The efficacy of position encoding in time series analysis is not well-studied and remains controversial, e.g., whether it is better to

Paulina Toro Isaza, Guangxuan Xu, Akintoye Oloko, Yufang Hou

Social biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literature analyzing such biases in children stories. Because these analyses are often conducted manually and at a small scale, such investigations can benefit from the use of more recent n

Bo Xie, Jianpeng Liu

In this work, we present a theoretical research on the lattice relaxations, phonon properties, and relaxed electronic structures in magic-angle twisted bilayer graphene (TBG). We construct a continuum elastic model in order to study the lattice dynamics of magic-angle TBG, where both in-plane and out-of-plane lattice displacements are take into account. The

Michael A. Kouritzin, Daniel Richard

A topological neural network (TNN), which takes data from a Tychonoff topological space instead of the usual finite dimensional space, is introduced. As a consequence, a distributional neural network (DNN) that takes Borel measures as data is also introduced. Combined these new neural networks facilitate things like recognizing long range dependence, heavy t

Shenglong Zhang, Ying Liu

Metaphor detection (MD) suffers from limited training data. In this paper, we started with a linguistic rule called Metaphor Identification Procedure and then proposed a novel multi-task learning framework to transfer knowledge in basic sense discrimination (BSD) to MD. BSD is constructed from word sense disambiguation (WSD), which has copious amounts of dat

Zhuohua Cai, Xiao Zhang

We investigate parallel spinors on the Eguchi-Hanson metrics and find the space of complex parallel spinors are complex 2-dimensional. For the metrics of Eguchi-Hanson type with the zero scalar curvature, we separate variables for the harmonic spinors and obtain the solutions explicitly.

Tao Yang, Zhichao Xu, Zhenduo Wang, Qingyao Ai

Ranking systems are the key components of modern Information Retrieval (IR) applications, such as search engines and recommender systems. Besides the ranking relevance to users, the exposure fairness to item providers has also been considered an important factor in ranking optimization. Many fair ranking algorithms have been proposed to jointly optimize both

Vijay Viswanathan, Luyu Gao, Tongshuang Wu, Pengfei Liu

Modern machine learning relies on datasets to develop and validate research ideas. Given the growth of publicly available data, finding the right dataset to use is increasingly difficult. Any research question imposes explicit and implicit constraints on how well a given dataset will enable researchers to answer this question, such as dataset size, modality,

Jaehun Jung, Peter West, Liwei Jiang, Faeze Brahman

We present Impossible Distillation, a novel framework for paraphrasing and sentence summarization, that distills a high-quality dataset and model from a low-quality teacher that itself cannot perform these tasks. Unlike prior works that rely on an extreme-scale teacher model (e.g., GPT3) or task-specific architecture, we hypothesize and verify the paraphrast

Kadina E. Johnston, Clara Fannjiang, Bruce J. Wittmann, Brian L. Hie

Directed evolution of proteins has been the most effective method for protein engineering. However, a new paradigm is emerging, fusing the library generation and screening approaches of traditional directed evolution with computation through the training of machine learning models on protein sequence fitness data. This chapter highlights successful applicati

Agam Shah, Sudheer Chava

Recently large language models (LLMs) like ChatGPT have shown impressive performance on many natural language processing tasks with zero-shot. In this paper, we investigate the effectiveness of zero-shot LLMs in the financial domain. We compare the performance of ChatGPT along with some open-source generative LLMs in zero-shot mode with RoBERTa fine-tuned on

Chniguir Mounira, Henchiri Jamel Eddine

This paper aims to test the relationship between investor sentiment and the profitability of stocks listed on two emergent financial markets, the Moroccan and Tunisian ones. Two indirect measures of investor sentiment are used, SENT and ARMS. These sentiment indicators show that there is an important relationship between the stocks returns and investor senti

Supawich Puengdang, Worawate Ausawalaithong, Phiratath Nopratanawong, Narongdech Keeratipranon

Real estate is a critical sector in Thailand's economy, which has led to a growing demand for a more accurate land price prediction approach. Traditional methods of land price prediction, such as the weighted quality score (WQS), are limited due to their reliance on subjective criteria and their lack of consideration for spatial variables. In this study, we

Adrien Gregorj, Zeynep Yücel, Francesco Zanlungo, Claudio Feliciani

Pedestrian groups are commonly found in crowds but research on their social aspects is comparatively lacking. To fill that void in literature, we study the dynamics of collision avoidance between pedestrian groups (in particular dyads) and individual pedestrians in an ecological environment, focusing in particular on (i) how such avoidance depends on the gro

Seok Hyun Byun, Svetlana Poznanović

Recently, Glasby and Paseman considered the following sequence of binomial sums $\{2^{-r}\sum_{i=0}^{r}\binom{m}{i}\}_{r=0}^{m}$ and showed that this sequence is unimodal and attains its maximum value at $r=\lfloor\frac{m}{3}\rfloor+1$ for $m\in\mathbb{Z}_{\geq0}\setminus\{0,3,6,9,12\}$. They also analyzed the asymptotic behavior of the maximum value of the

Rongpu Zhou, Arjun Dey, Dustin Lang, John Moustakas

The relative photometric calibration errors in the DESI Legacy Imaging Surveys (LS), which are used for DESI target selection, can leave imprints on the DESI target densities and bias the resulting cosmological measurements. We characterize the LS calibration systematics by comparing the LS stellar photometry with Gaia DR3 synthetic photometry. We find the s

Yekun Yang, Xiao Zhang

Geodesic equations are solved when at least two of $\theta$, $\phi$ and $\psi$ are constant, or $r$ is constant, on scalar flat metrics of Eguchi-Hanson type. They can also be solved also on Eguchi-Hanson metrics which are Ricci flat if only $\phi$ is constant. However, the explicit solution of the geodesic equations is not available yet if only $\psi$ is co

Christoph Coijanovic, Christiane Kuhn, Thorsten Strufe

Anycast messaging (i.e., sending a message to an unspecified receiver) has long been neglected by the anonymous communication community. An anonymous anycast prevents senders from learning who the receiver of their message is, allowing for greater privacy in areas such as political activism and whistleblowing. While there have been some protocol ideas propos

Deepan Balakrishnan, Anupama Prakash, Benedikt J. Daurer, Cédric Finet

How pigment distribution influences the cuticle density within a microscopic butterfly wing scale, and how both impact each scale's final reflected color, remains unknown. We use ptychographic X-ray computed tomography to quantitatively determine, at nanoscale resolutions, the three-dimensional mass density of scales with pigmentation differences. By compari

Ivan Panin, Anastasia Stavrova

Let $X$ be a Noetherian separated scheme. Let $G$ be a reductive $X$-group scheme, and let $E$ be a principal $G$-bundle over $\mathbb{P}^1_X$. We prove that if the restriction of $E$ to $\infty\times X$ is Zariski locally trivial, then $E$ is itself Zariski locally trivial.

Shinhyeok Oh, Hyojun Go, Hyeongdon Moon, Yunsung Lee

Question generation (QG) is the task of generating a valid and fluent question based on a given context and the target answer. According to various purposes, even given the same context, instructors can ask questions about different concepts, and even the same concept can be written in different ways. However, the evaluation for QG usually depends on single

Bruno Andreis, Soro Bedionita, Philip H. S. Torr, Sung Ju Hwang

We propose a neural network weight encoding method for network property prediction that utilizes set-to-set and set-to-vector functions to efficiently encode neural network parameters. Our approach is capable of encoding neural networks in a model zoo of mixed architecture and different parameter sizes as opposed to previous approaches that require custom en

Osamu Seto, Tomo Takahashi, Yo Toda

We point out that the recent result of primordial helium-4 ($^4$He) abundance measurement by EMPRESS, which has reported a smaller $^4$He abundance than other measurements, can be well fitted by assuming a time-variation of the fine structure constant $\alpha$ which is slightly smaller than the present value during big bang nucleosynthesis (BBN). We find tha

ATLAS Collaboration

The ATLAS detector is installed in its experimental cavern at Point 1 of the CERN Large Hadron Collider. During Run 2 of the LHC, a luminosity of $\mathcal{L}=2\times 10^{34}\mathrm{cm}^{-2}\mathrm{s}^{-1}$ was routinely achieved at the start of fills, twice the design luminosity. For Run 3, accelerator improvements, notably luminosity levelling, allow susta

Chen Wang, Xu Wu, Tomasz Kozlowski

Inverse Uncertainty Quantification (IUQ) method has been widely used to quantify the uncertainty of Physical Model Parameters (PMPs) in nuclear Thermal Hydraulics (TH) systems. This paper introduces a novel hierarchical Bayesian model which aims to mitigate two existing challenges in IUQ: the high variability of PMPs under varying experimental conditions, an

Sukai Huang, Nir Lipovetzky, Trevor Cohn

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framework, LRS involves training a reward function that rewards behaviours precisely aligned with given language instructions. We argue that the a

Anshul Nayak, Azim Eskandarian, Zachary Doerzaph, Prasenjit Ghorai

One of the fundamental challenges in the prediction of dynamic agents is robustness. Usually, most predictions are deterministic estimates of future states which are over-confident and prone to error. Recently, few works have addressed capturing uncertainty during forecasting of future states. However, these probabilistic estimation methods fail to account f

Oleg Rybakov, Phoenix Meadowlark, Shaojin Ding, David Qiu

Large speech models are rapidly gaining traction in research community. As a result, model compression has become an important topic, so that these models can fit in memory and be served with reduced cost. Practical approaches for compressing automatic speech recognition (ASR) model use int8 or int4 weight quantization. In this study, we propose to develop 2

Daeho Um, Jiwoong Park, Seulki Park, Jin Young Choi

This paper investigates a missing feature imputation problem for graph learning tasks. Several methods have previously addressed learning tasks on graphs with missing features. However, in cases of high rates of missing features, they were unable to avoid significant performance degradation. To overcome this limitation, we introduce a novel concept of channe

Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng

The detection of machine-generated text, especially from large language models (LLMs), is crucial in preventing serious social problems resulting from their misuse. Some methods train dedicated detectors on specific datasets but fall short in generalizing to unseen test data, while other zero-shot ones often yield suboptimal performance. Although the recent

Jianhua Zhang, Jiaxin Lin, Pan Tang, Yuxiang Zhang

Sixth-generation (6G) mobile communications have attracted substantial attention in the global research community of information and communication technologies (ICTs). 6G systems are expected to support not only extended 5G usage scenarios but also new usage scenarios, such as integrated sensing and communication (ISAC), integrated artificial intelligence (A

Michael Fu, Chakkrit Tantithamthavorn, Trung Le, Yuki Kume

Many ML-based approaches have been proposed to automatically detect, localize, and repair software vulnerabilities. While ML-based methods are more effective than program analysis-based vulnerability analysis tools, few have been integrated into modern IDEs, hindering practical adoption. To bridge this critical gap, we propose AIBugHunter, a novel ML-based s

Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo

This paper proposes the Phy-DRL: a physics-regulated deep reinforcement learning (DRL) framework for safety-critical autonomous systems. The Phy-DRL has three distinguished invariant-embedding designs: i) residual action policy (i.e., integrating data-driven-DRL action policy and physics-model-based action policy), ii) automatically constructed safety-embedd

Dana Z. Anderson, Katarzyna Krzyzanowska

A gauge field treatment of a current, oscillating at a fixed frequency, of interacting neutral atoms leads to a set of matter-wave duals to Maxwell's equations for the electromagnetic field. In contrast to electromagnetics, the velocity of propagation has a lower limit rather than upper limit and the wave impedance of otherwise free space is negative real-va

Rui Hao, Dianbo Liu, Linmei Hu

The merging of human intelligence and artificial intelligence has long been a subject of interest in both science fiction and academia. In this paper, we introduce a novel concept in Human-AI interaction called Symbiotic Artificial Intelligence with Shared Sensory Experiences (SAISSE), which aims to establish a mutually beneficial relationship between AI sys

Michael Fu, Trung Le, Van Nguyen, Chakkrit Tantithamthavorn

Deep learning (DL) models have become increasingly popular in identifying software vulnerabilities. Prior studies found that vulnerabilities across different vulnerable programs may exhibit similar vulnerable scopes, implicitly forming discernible vulnerability patterns that can be learned by DL models through supervised training. However, vulnerable scopes

Haodong He, Hao Fu, Qiang Wang, Shuai Zhou

The social robot navigation is an open and challenging problem. In existing work, separate modules are used to capture spatial and temporal features, respectively. However, such methods lead to extra difficulties in improving the utilization of spatio-temporal features and reducing the conservative nature of navigation policy. In light of this, we present a

Shinji Koide, Masaaki Takahashi, Rohta Takahashi

A linear analysis based on two-fluid equations in the approximation of a cold plasma, wherein the plasma temperature is assumed to be zero, demonstrates that a two-stream instability occurs in all cases. However, if this were true, the drift motion of electrons in an electric current over a wire would become unstable, inducing an oscillation in an electric c

Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Atsushi Iwasaki

This paper proposes a payoff perturbation technique for the Mirror Descent (MD) algorithm in games where the gradient of the payoff functions is monotone in the strategy profile space, potentially containing additive noise. The optimistic family of learning algorithms, exemplified by optimistic MD, successfully achieves {\it last-iterate} convergence in scen

Ye Yan, Yuheng Wu, Hongxia Huang, Jialun Ping

Inspired by the fully heavy tetraquark states reported by the LHCb, ATLAS and CMS Collaborations, we perform a systemical investigation of the low-lying fully heavy pentaquark systems composed of charm and bottom quarks (anti-quark) in the chiral quark model. With the help of the channel-coupling, we obtain several fully heavy pentaquark candidates, which ar

Yi-Chiao Wu, Israel D. Gebru, Dejan Marković, Alexander Richard

A good audio codec for live applications such as telecommunication is characterized by three key properties: (1) compression, i.e.\ the bitrate that is required to transmit the signal should be as low as possible; (2) latency, i.e.\ encoding and decoding the signal needs to be fast enough to enable communication without or with only minimal noticeable delay;

C. L. Van Eck, B. M. Gaensler, S. Hutschenreuter, J. Livingston

Faraday rotation measures (RMs) have been used for many studies of cosmic magnetism, and in most cases having more RMs is beneficial for those studies. This has lead to development of RM surveys that have produced large catalogs, as well as meta-catalogs collecting RMs from many different publications. However, it has been difficult to take full advantage of

Tao Yang, Cuize Han, Chen Luo, Parth Gupta

Ranking is at the core of many artificial intelligence (AI) applications, including search engines, recommender systems, etc. Modern ranking systems are often constructed with learning-to-rank (LTR) models built from user behavior signals. While previous studies have demonstrated the effectiveness of using user behavior signals (e.g., clicks) as both feature

Guan Wang, Weihua Li, Edmund M-K. Lai, Quan Bai

The rapid growth of information on the Internet has led to an overwhelming amount of opinions and comments on various activities, products, and services. This makes it difficult and time-consuming for users to process all the available information when making decisions. Text summarization, a Natural Language Processing (NLP) task, has been widely explored to

Shiyu Li, Ho-Chun Lin, Chia Wei Hsu

Computer-automated design and discovery have led to high-performance nanophotonic devices with diverse functionalities. However, massively multi-channel systems such as metasurfaces controlling many incident angles and photonic-circuit components coupling many waveguide modes still present a challenge. Conventional methods require $M_{\rm in}$ forward simula

Ziang Meng, Han Yan, Peixin Qin, Xiaorong Zhou

Topotactic transition is a structural phase change in a matrix crystal lattice mediated by the ordered loss/gain and rearrangement of atoms, leading to unusual coordination environments and metal atoms with rare valent states. As early as in 1990s, low temperature hydride reduction was utilized to realize the topotactic transition. Since then, topological tr

F. E. Onah, B. R. Jaramillo-Ávila, F. H. Maldonado-Villamizar, B. M. Rodríguez-Lara

We present a Hamiltonian model describing two pairs of mechanical and optical modes under standard optomechanical interaction. The vibrational modes are mechanically isolated from each other and the optical modes couple evanescently. We recover the ranges for variables of interest, such as mechanical and optical resonant frequencies and naked coupling streng

Yang He, Vassiliy Lubchenko

We argue that one can associate a pseudo-time with sequences of configurations generated in the course of classical Monte Carlo simulations for a single-minimum bound state, if the sampling is optimal. Hereby the sampling rates can be, under special circumstances, calibrated against the relaxation rate and frequency of motion of an actual physical system. Th

Sanjoy Kundu, Shubham Trehan, Sathyanarayanan N. Aakur

Learning to infer labels in an open world, i.e., in an environment where the target ``labels'' are unknown, is an important characteristic for achieving autonomy. Foundation models, pre-trained on enormous amounts of data, have shown remarkable generalization skills through prompting, particularly in zero-shot inference. However, their performance is restric

Zeng-hui Yang, Yang Liu, Ning An, Xingyu Chen

Neutron and $\gamma$-ray irradiation damages to transistors are found to be non-additive, and this is denoted as the irradiation synergistic effect (ISE). Its mechanism is not well-understood. The recent defect-based model [ACS Appl. Electron. Mater. 2, 3783 (2020)] for Silicon bipolar junction transistors (BJT) achieve quantitative agreement with experiment

Ollin D. Langle-Chimal, Scott C. Merrill, Eric M. Clark, Gabriela Bucini

Human behavior is a dynamic process that evolves with experience. Understanding the evolution of individual's risk propensity is critical to design public health interventions to propitiate the adoption of better biosecurity protocols and thus, prevent the transmission of an infectious disease. Using an experimental game that simulates the spread of a diseas

Zhiwei Cao, Baosong Yang, Huan Lin, Suhang Wu

$k$-Nearest neighbor machine translation ($k$NN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains. By using an upstream NMT model to traverse the downstream training corpus, it is equipped with a datastore containing vectorized key-value pairs, which are retrieved during inference to benefit tran

Farhad Moghimifar, Shilin Qu, Tongtong Wu, Yuan-Fang Li

Norms, which are culturally accepted guidelines for behaviours, can be integrated into conversational models to generate utterances that are appropriate for the socio-cultural context. Existing methods for norm recognition tend to focus only on surface-level features of dialogues and do not take into account the interactions within a conversation. To address

Neal Lawton, Anoop Kumar, Govind Thattai, Aram Galstyan

Parameter-efficient tuning (PET) methods fit pre-trained language models (PLMs) to downstream tasks by either computing a small compressed update for a subset of model parameters, or appending and fine-tuning a small number of new model parameters to the pre-trained network. Hand-designed PET architectures from the literature perform well in practice, but ha

Mingyang Liu, Fu Song, Taolue Chen

Masking is a widely-used effective countermeasure against power side-channel attacks for implementing cryptographic algorithms. Surprisingly, few formal verification techniques have addressed a fundamental question, i.e., whether the masked program and the original (unmasked) cryptographic algorithm are functional equivalent. In this paper, we study this pro

Yi-Tong Wang, Jiao Ma, Xing-Yu Han, Xin-Xin Long

We study lepton flavor violating (LFV) decays $B^0\rightarrow{{l_i}^{\pm}{l_j}^{\mp}}$ ($B^0\rightarrow e{\mu}$, $B^0\rightarrow e{\tau}$ and $B^0\rightarrow {\mu}{\tau}$) in the $U(1)_X$SSM (SSM is acronym for the supersymmetric standard model), which is the $U(1)_X$ extension of the minimal supersymmetric standard model (MSSM). The local gauge group of $U(

Xinyi Chen, Qu Yang, Jibin Wu, Haizhou Li

Recently, brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks. However, these SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation. Given that each neural coding scheme possesses its own merits and drawbacks, these SNNs encounter ch

Karan Taneja, Xiaolong He, Qizhi He, J. S. Chen

This work presents a multi-resolution physics-informed recurrent neural network (MR PI-RNN), for simultaneous prediction of musculoskeletal (MSK) motion and parameter identification of the MSK systems. The MSK application was selected as the model problem due to its challenging nature in mapping the high-frequency surface electromyography (sEMG) signals to t

Yiyun He, Thomas Strohmer, Roman Vershynin, Yizhe Zhu

Differentially private synthetic data provide a powerful mechanism to enable data analysis while protecting sensitive information about individuals. However, when the data lie in a high-dimensional space, the accuracy of the synthetic data suffers from the curse of dimensionality. In this paper, we propose a differentially private algorithm to generate low-d

Xipin Wei, Junhui Chen, Zirui Zheng, Li Guo

Recently, multi-instrument music generation has become a hot topic. Different from single-instrument generation, multi-instrument generation needs to consider inter-track harmony besides intra-track coherence. This is usually achieved by composing note segments from different instruments into a signal sequence. This composition could be on different scales,

Zhaowei Zhang, Ceyao Zhang, Nian Liu, Siyuan Qi

The emergent capabilities of Large Language Models (LLMs) have made it crucial to align their values with those of humans. However, current methodologies typically attempt to assign value as an attribute to LLMs, yet lack attention to the ability to pursue value and the importance of transferring heterogeneous values in specific practical applications. In th

Tao Xiao, Sebastian Baltes, Hideaki Hata, Christoph Treude

Commit messages contain diverse and valuable types of knowledge in all aspects of software maintenance and evolution. Links are an example of such knowledge. Previous work on "9.6 million links in source code comments" showed that links are prone to decay, become outdated, and lack bidirectional traceability. We conducted a large-scale study of 18,201,165 li

Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen

This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a policy that optimizes the worst-case performance when the deployed environment falls within a prescribed uncertainty set around the nominal

Jie Sun, Li Su, Zuocheng Shi, Wenting Shen

Graph neural network(GNN) has been widely applied in real-world applications, such as product recommendation in e-commerce platforms and risk control in financial management systems. Several cache-based GNN systems have been built to accelerate GNN training in a single machine with multiple GPUs. However, these systems fail to train billion-scale graphs effi

Anurag Adityanarayan Ray, Ashoke De

The present numerical investigation focuses on the leading edge bluntness effects on the double-wedge with varied aft-wedge angles exposed to low enthalpy hypersonic free stream conditions. The bluntness ratio in this study varies, ranging from R/L1 = 0 (sharp leading edge) to R/L1 = 0.577 (maximum allowable bluntness), along with the aft-wedge angle varying

Hai-Chao Zhang

By adding a matter-coupled dark energy field to Einstein's General Relativity (GR), this paper proves that the dynamical dark energy field can change the frequency of photons from distant galaxies as well as from background radiation of remote Universe. Therefore, when the observed frequency-shift of the photons is entirely attributed to the temporal variati

Kuan-Hao Huang, Varun Iyer, I-Hung Hsu, Anoop Kumar

Paraphrase generation is a long-standing task in natural language processing (NLP). Supervised paraphrase generation models, which rely on human-annotated paraphrase pairs, are cost-inefficient and hard to scale up. On the other hand, automatically annotated paraphrase pairs (e.g., by machine back-translation), usually suffer from the lack of syntactic diver

Slimane Adjerid, Tao Lin, Haroun Meghaichi

It has been noted that the traditional scaling argument cannot be directly applied to the error analysis of immersed finite elements (IFE) because, in general, the spaces on the reference element associated with the IFE spaces on different interface elements via the standard affine mapping are not the same. By analyzing a mapping from the involved Sobolev sp

Hyungki Im, Paul Grigas

We consider distributionally robust optimization (DRO) problems, reformulated as distributionally robust feasibility (DRF) problems, with multiple expectation constraints. We propose a generic stochastic first-order meta-algorithm, where the decision variables and uncertain distribution parameters are each updated separately by applying stochastic first-orde

Hang Zhou, Jonas Mueller, Mayank Kumar, Jane-Ling Wang

Noise plagues many numerical datasets, where the recorded values in the data may fail to match the true underlying values due to reasons including: erroneous sensors, data entry/processing mistakes, or imperfect human estimates. We consider general regression settings with covariates and a potentially corrupted response whose observed values may contain erro

Yao Yao, Zuchao Li, Hai Zhao

With the widespread use of language models (LMs) in NLP tasks, researchers have discovered the potential of Chain-of-thought (CoT) to assist LMs in accomplishing complex reasoning tasks by generating intermediate steps. However, human thought processes are often non-linear, rather than simply sequential chains of thoughts. Therefore, we propose Graph-of-Thou

Adam Wiemerslage, Changbing Yang, Garrett Nicolai, Miikka Silfverberg

With a growing focus on morphological inflection systems for languages where high-quality data is scarce, training data noise is a serious but so far largely ignored concern. We aim at closing this gap by investigating the types of noise encountered within a pipeline for truly unsupervised morphological paradigm completion and its impact on morphological inf

Xue Zhang, Xiaohan Zhang, Jiangtao Wang, Jiacheng Ying

Pedestrian detection plays a critical role in computer vision as it contributes to ensuring traffic safety. Existing methods that rely solely on RGB images suffer from performance degradation under low-light conditions due to the lack of useful information. To address this issue, recent multispectral detection approaches have combined thermal images to provi

Shane Storks, Keunwoo Peter Yu, Ziqiao Ma, Joyce Chai

As natural language processing (NLP) has recently seen an unprecedented level of excitement, and more people are eager to enter the field, it is unclear whether current research reproducibility efforts are sufficient for this group of beginners to apply the latest developments. To understand their needs, we conducted a study with 93 students in an introducto

Ming Zhang, Qi Meng, Deng Zhang, Yue Wang

The numerical determination of solitary states is an important topic for such research areas as Bose-Einstein condensates, nonlinear optics, plasma physics, etc. In this paper, we propose a data-driven approach for identifying solitons based on dynamical solutions of real-time differential equations. Our approach combines a machine-learning architecture call

Eric Silk, Swarnita Chakraborty, Nairanjana Dasgupta, Anand D. Sarwate

Training deep neural networks (DNNs) used in modern machine learning is computationally expensive. Machine learning scientists, therefore, rely on stochastic first-order methods for training, coupled with significant hand-tuning, to obtain good performance. To better understand performance variability of different stochastic algorithms, including second-orde

Sanjay M. Joshi

Computational method for statistical measures of reliability, confidence, and assurance are available for infinite population size. If the population size is finite and small compared to the number of samples tested, these computational methods need to be improved for a better representation of reality. This article discusses how to compute reliability, conf

Haozhe An, Rachel Rudinger

Through the use of first name substitution experiments, prior research has demonstrated the tendency of social commonsense reasoning models to systematically exhibit social biases along the dimensions of race, ethnicity, and gender (An et al., 2023). Demographic attributes of first names, however, are strongly correlated with corpus frequency and tokenizatio

S. Xu, R. Li, Y. Zhai, Y. Xia

Direct laser cooling and trapping of molecules to temperature below Doppler limit and density exceeding $10^8$ are challenging due to the sub-Doppler heating effects of molecular magneto-optical trap (MOT). In our previous paper [1], we presented a general approach to engineering the sub- Doppler force by tuning the AC stark shift with the addition of a blue

Jorgen D'Hondt, Tae Jeong Kim

At the LHC, the process of a Higgs boson decaying into bottom or charm quarks produced in association with a pair of top quarks, ttbarH , allows for an empirical exploration of the heavy-flavor quark Yukawa couplings to the Higgs boson. Accordingly, the cross-sections for the $t\bar{t}$ + heavy-flavor production without the appearance of the Higgs boson have

Giulio Camillo, Víctor H. Cervantes

Several principled measures of contextuality have been proposed for general systems of random variables (i.e. inconsistentlly connected systems). The first of such measures was based on quasi-couplings using negative probabilities (here denoted by CNT3, Dzhafarov & Kujala, 2016). Dzhafarov and Kujala (2019) introduced a measure of contextuality, CNT2, that n

Naoya Hasegawa, Issei Sato

Recognition problems in long-tailed data, in which the sample size per class is heavily skewed, have gained importance because the distribution of the sample size per class in a dataset is generally exponential unless the sample size is intentionally adjusted. Various methods have been devised to address these problems.Recently, weight balancing, which combi