October 2023 arXiv papers — page 64

Younwoo Choi, Ray Coden Mercurius, Soheil Mohamad Alizadeh Shabestary, Amir Rasouli

Road user trajectory prediction in dynamic environments is a challenging but crucial task for various applications, such as autonomous driving. One of the main challenges in this domain is the multimodal nature of future trajectories stemming from the unknown yet diverse intentions of the agents. Diffusion models have shown to be very effective in capturing

Minghao Tang, Yongquan He, Yongxiu Xu, Hongbo Xu

Named entity recognition (NER) is a fundamental task in natural language processing that aims to identify and classify named entities in text. However, span-based methods for NER typically assign entity types to text spans, resulting in an imbalanced sample space and neglecting the connections between non-entity and entity spans. To address these issues, we

Hironori Yamaguchi, Satoshi Morota, Takanori Kida, Seiya Shimono

We successfully synthesized ($p$-Py-V)[Cu(hfac)$_2$], a verdazyl-based complex. Molecular orbital calculations revealed five types of intermolecular interactions between the radical spins and two types of intramolecular interactions between the radical and the Cu spins, resulting in a spin-1/2 distorted honeycomb-based lattice. Additionally, competing ferrom

Tianjun Gan

HD 175167b is a cold ($P_{b}\sim 1200$ days) Jupiter with a minimum mass of $M_{p}\sin i=7.8\pm3.5\ M_J$ orbiting a Sun-like star, first discovered by the Magellan Planet Search Program based on MIKE observations. Through a joint analysis of the MIKE data and the Gaia two-body orbital solution, Winn (2022) found a companion mass of $M_{p}=14.8\pm1.8\ M_J$ an

Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian

We introduce HallusionBench, a comprehensive benchmark designed for the evaluation of image-context reasoning. This benchmark presents significant challenges to advanced large visual-language models (LVLMs), such as GPT-4V(Vision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, by emphasizing nuanced understanding and interpretation of visual data. The benchmar

Rasoul Akhavan Mahdavi, Nils Lukas, Faezeh Ebrahimianghazani, Thomas Humphries

Two parties with private data sets can find shared elements using a Private Set Intersection (PSI) protocol without revealing any information beyond the intersection. Circuit PSI protocols privately compute an arbitrary function of the intersection - such as its cardinality, and are often employed in an unbalanced setting where one party has more data than t

Jian Guan, Jesse Dodge, David Wadden, Minlie Huang

Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs). Nevertheless, LLMs frequently "hallucinate," resulting in non-factual outputs. Our carefully-designed human evaluation substantiates the serious hallucination issue, revealing that even GPT-3.5 produces factual outputs less than 25% of the t

Oliver Li, Mallika Subramanian, Arkadiy Saakyan, Sky CH-Wang

Social norms fundamentally shape interpersonal communication. We present NormDial, a high-quality dyadic dialogue dataset with turn-by-turn annotations of social norm adherences and violations for Chinese and American cultures. Introducing the task of social norm observance detection, our dataset is synthetically generated in both Chinese and English using a

E. I. Kaptsov

Despite the large number of publications on symmetry analysis of the geopotential forecast equation, its group foliations laws have not been considered previously. The present publication aims to address this shortcoming. First, group foliations are constructed for the equation, and based on them, invariant solutions are derived, some of which generalize pre

Tian Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera

We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. Moreover, unlike vector-based representations, distribution-based represe

Yaguan Qian, Chenyu Zhao, Zhaoquan Gu, Bin Wang

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical diagnosis. At present, adversarial training is one of the most effective defenses against adversarial examples. However, traditi

Hui Tian, Kai Xu

Point cloud reconstruction from raw point cloud has been an important topic in computer graphics for decades, especially due to its high demand in modeling and rendering applications. An important way to solve this problem is establishing a local geometry to fit the local curve. However, previous methods build either a local plane or polynomial curve. Local

Alexandre Jacquillat, Michael Lingzhi Li, Martin Ramé, Kai Wang

Predictive contagion models are ubiquitous in epidemiology, social sciences, engineering, and management. This paper formulates a prescriptive contagion analytics model where a decision-maker allocates shared resources across multiple segments of a population, each governed by continuous-time dynamics. We define four real-world problems under this umbrella:

Ghadi Nehme, Tejas Y. Deo

Autonomous vehicles have the potential to revolutionize transportation, but they must be able to navigate safely in traffic before they can be deployed on public roads. The goal of this project is to train autonomous vehicles to make decisions to navigate in uncertain environments using deep reinforcement learning techniques using the CARLA simulator. The si

Xinlu Zhang, Chenxin Tian, Xianjun Yang, Lichang Chen

Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications. However, previous studies mainly fine-tune LLMs on biomedical datasets with limited diversity, which often rely on benchmarks or narrow task scopes, and hence significantly limit the effectiv

Chiyu Zhang, Khai Duy Doan, Qisheng Liao, Muhammad Abdul-Mageed

Instruction tuned large language models (LLMs), such as ChatGPT, demonstrate remarkable performance in a wide range of tasks. Despite numerous recent studies that examine the performance of instruction-tuned LLMs on various NLP benchmarks, there remains a lack of comprehensive investigation into their ability to understand cross-lingual sociopragmatic meanin

Taiki Sugiura, Toru Tamaki

Action recognition is a well-established area of research in computer vision. In this paper, we propose S3Aug, a video data augmenatation for action recognition. Unlike conventional video data augmentation methods that involve cutting and pasting regions from two videos, the proposed method generates new videos from a single training video through segmentati

Anshuman Pradhan, Kyra H. Adams, Venkat Chandrasekaran, Zhen Liu

Modeling groundwater levels continuously across California's Central Valley (CV) hydrological system is challenging due to low-quality well data which is sparsely and noisily sampled across time and space. The lack of consistent well data makes it difficult to evaluate the impact of 2017 and 2019 wet years on CV groundwater following a severe drought during

Runzhe Wu, Wen Sun

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be efficient in terms of statistical complexity, computational complexity, and query complexity. In this work, we consider the RLHF setting where the feedback is given in the format of preferences over pairs of trajectories. In the linear MDP model, using randomization in algorit

Aref Sayareh, Aria Sardari, Vahid Khoddami, Nader Zare

The RoboCup competitions hold various leagues, and the Soccer Simulation 2D League is a major among them. Soccer Simulation 2D (SS2D) match involves two teams, including 11 players and a coach for each team, competing against each other. The players can only communicate with the Soccer Simulation Server during the game. Several code bases are released public

Ahmad Wisnu Mulyadi, Heung-Il Suk

Extensive adoption of electronic health records (EHRs) offers opportunities for their use in various downstream clinical analyses. To accomplish this purpose, enriching an EHR cohort with external knowledge (e.g., standardized medical ontology and wealthy semantics) could help us reveal more comprehensive insights via a spectrum of informative relations amon

Claude Duhr, Paarth Thakkar

Numerical approaches to computations typically reconstruct the numerators of Feynman diagrams in four dimensions. In doing so, certain rational terms arising from the (D-4)-dimensional part of the numerator multiplying ultraviolet (UV) poles in dimensional regularisation are not captured and need to be obtained by other means. At one-loop these rational term

Chenlu Ye, Rui Yang, Quanquan Gu, Tong Zhang

We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the offline dataset, and the corruption level $\zeta\geq0$ quantifies the cumulative corruption amount over $n$ episodes and $H$ steps. Our goal is to find a policy that is robust to suc

Khanh-Tung Tran, Truong Son Hy, Lili Jiang, Xuan-Son Vu

Accurate forecasting and analysis of emerging pandemics play a crucial role in effective public health management and decision-making. Traditional approaches primarily rely on epidemiological data, overlooking other valuable sources of information that could act as sensors or indicators of pandemic patterns. In this paper, we propose a novel framework called

Md Rakib Hossain Misu, Jiawei Li, Adithya Bhattiprolu, Yang Liu

Traditionally, energy efficiency research has focused on reducing energy consumption at the hardware level and, more recently, in the design and coding phases of the software development life cycle. However, software testing's impact on energy consumption did not receive attention from the research community. Specifically, how test code design quality and te

Muhammad Umair, Athman Bouguettaya, Abdallah Lakhdari

We propose a novel service framework to detect changes in crowdsourced images. We use a service-oriented approach to model and represent crowdsourced images as image services. Non-functional attributes of an image service are leveraged to detect changes in an image. The changes are reported in form of a version tree. The version tree is constructed in a way

Li-Ying Chou, Yi-Zen Chu, Yen-Wei Liu

We point out, the scalar sector of gravitational perturbations may be excited by an isolated astrophysical system immersed in a universe whose accelerated expansion is not due to the cosmological constant, but due to extra field degrees of freedom. This is true even if the source of gravitational radiation did not couple directly to these additional fields.

Xianjue Zhao, Peiyun Ge, Hongye Yu, Li You

With qubits encoded into atomic ground and Rydberg states and situated on the vertexes of a graph, the conditional quantum dynamics of Rydberg blockade, which inhibits simultaneous excitation of nearby atoms, has been employed recently to find maximum independent sets following an adiabatic evolution algorithm hereafter denoted by HV [Science 376, 1209 (2022

V Vien Lee, Stephanie C. C. van der Lubbe, Lay Hoon Goh, Jose M. Valderas

ChatGPT is an advanced natural language processing tool with growing applications across various disciplines in medical research. Thematic analysis, a qualitative research method to identify and interpret patterns in data, is one application that stands to benefit from this technology. This viewpoint explores the utilization of ChatGPT in three core phases o

Kevin Li, Max Balakirsky, Simon Mak

Fourier feature approximations have been successfully applied in the literature for scalable Gaussian Process (GP) regression. In particular, Quadrature Fourier Features (QFF) derived from Gaussian quadrature rules have gained popularity in recent years due to their improved approximation accuracy and better calibrated uncertainty estimates compared to Rando

Syed Waqar Ali Shah

Kolyvagin introduced the method of Euler systems to study the structure of Selmer groups of elliptic curves. In this semi-expository article, we prove the horizontal norm relations for the CM points on modular curves underlying Kolyvagin's Euler system, with a view toward higher-dimensional generalizations.

Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu

While recent studies have looked into the abilities of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc, there have been few studies looking into the controllability of large language models on generation tasks. We present an extensive analysis of various benchmarks including a sente

Duzhen Zhang, Wei Cong, Jiahua Dong, Yahan Yu

Continual Named Entity Recognition (CNER) is a burgeoning area, which involves updating an existing model by incorporating new entity types sequentially. Nevertheless, continual learning approaches are often severely afflicted by catastrophic forgetting. This issue is intensified in CNER due to the consolidation of old entity types from previous steps into t

Yutaro Yamada, Yihan Bao, Andrew K. Lampinen, Jungo Kasai

Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM representations implicitly capture aspects of the underlying grounded concepts. Here, we explore LLM representations of a particularly salient kind of grounded knowledge -- spatial relat

Jeffrey Lang

We present several versions of the Jacobian Conjecture in positive characteristic each of which if true would imply the Jacobian conjecture in characteristic 0. We test these characteristic p versions of the conjecture against several families of Jacobian pairs in characteristic p. Based on the results we propose a characteristic p approach to solving the Ja

Mark E. AlSukaiti, Nafaa Chbili

We prove that the Alexander polynomials of certain families of alternating 4-braid knots satisfy Fox's Trapezoidal Conjecture. Moreover, we give explicit formulas for the signature and for the first 4 coefficients of the Alexander polynomial for a large family of alternating $n$-braid links and we verify that these 4 coefficients form a log-concave sequence.

Xumin Pu, Zhinan Sun, Qianbin Chen, Shi Jin

This paper investigates the low-complex linear minimum mean squared error (LMMSE) channel estimation in an extra-large scale MIMO system with the spherical wave model (SWM). We model the extra-large scale MIMO channels using the SWM in the terahertz (THz) line-of-sight propagation, in which the transceiver is a uniform circular antenna array. On this basis,

S. R. Mane

This note analyzes properties of the median $\nu$ of the Poisson distribution of order $k$. Given a value for the median in the interval $\nu\in[1,k]$, an equation to calculate the corresponding value of the rate parameter $\lambda$ is derived. Numerical evidence is presented that the value of the median exhibits many scaling properties, which permit one to

Xin Du, Kai Moriyama, Kumiko Tanaka-Ishii

This paper shows a novel machine learning model for realized volatility (RV) prediction using a normalizing flow, an invertible neural network. Since RV is known to be skewed and have a fat tail, previous methods transform RV into values that follow a latent distribution with an explicit shape and then apply a prediction model. However, knowing that shape is

Hadyan Luthfan Prihadi, Freddy Permana Zen, Donny Dwiputra, Seramika Ariwahjoedi

The butterfly velocity of four-dimensional rotating charged asymptotically AdS black hole is calculated to probe chaos using localized rotating shock waves. In this work, we obtain the angular momentum dependence of the butterfly velocity due to rotation in the shock wave probes. In general, the angular momentum $\mathcal{L}$ of the shock waves increases the

Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang

The sequence-to-sequence (Seq2Seq) approach has recently been widely used in grammatical error correction (GEC) and shows promising performance. However, the Seq2Seq GEC approach still suffers from two issues. First, a Seq2Seq GEC model can only be trained on parallel data, which, in GEC task, is often noisy and limited in quantity. Second, the decoder of a

Heinrich Peters, Yozen Liu, Francesco Barbieri, Raiyan Abdul Baten

The success of online social platforms hinges on their ability to predict and understand user behavior at scale. Here, we present data suggesting that context-aware modeling approaches may offer a holistic yet lightweight and potentially privacy-preserving representation of user engagement on online social platforms. Leveraging deep LSTM neural networks to a

Hengchang Guo, Qilong Zhang, Junwei Luo, Feng Guo

Deep learning based blind watermarking works have gradually emerged and achieved impressive performance. However, previous deep watermarking studies mainly focus on fixed low-resolution images while paying less attention to arbitrary resolution images, especially widespread high-resolution images nowadays. Moreover, most works usually demonstrate robustness

Jia Shi

In this paper, we prove that if a solution to the Muskat problem with different densities and the same viscosity is sufficiently smooth, the solution is analytic in a region that degenerates at the turnover points, provided some additional conditions are satisfied. This paper studies the analyticity of the solution near turnover points, complementing the res

Lin Tang, Weipeng Lin, Yang Wang, Jing Li

In this paper, by analyzing mock images from the IllustrisTNG100-1 simulation, we examine the properties of the diffuse light and compare them to those of central and satellite galaxies. Our findings suggest that the majority of the diffuse light originates from satellites. This claim is supported by the similarity between the age and metallicity distributio

Rei Inoue, Atsuo Kuniba, Yuji Terashima

We develop the quantum cluster algebra approach recently introduced by Sun and Yagi to investigate the tetrahedron equation, a three-dimensional generalization of the Yang-Baxter equation. In the case of square quiver, we devise a new realization of quantum Y-variables in terms $q$-Weyl algebras and obtain a solution that possesses three spectral parameters.

D. D. Ofengeim, P. S. Shternin, T. Piran

We propose a universal approximation of the equation of state of superdense matter in neutron star (NS) interiors. It contains only two parameters, the pressure and the density at the center of the maximally massive neutron star. We demonstrate the validity of this approximation for a wide range of different types of equations of state, including both baryon

Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang

Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests. However, current approaches generally integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with exte

Xiaotian Han, Kaixiong Zhou, Ting-Hsiang Wang, Jundong Li

In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g., age and gender), the fairness incurred by the graph structure should also be given attention. On the other han

Yunfan Zhao, Nikhil Behari, Edward Hughes, Edwin Zhang

Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning perspective. Prior RMAB research suffers from several limitations, e.g., it fails to adequately address continuous states, a

Yulan Hu, Sheng Ouyang, Jingyu Liu, Ge Chen

Graph contrastive learning (GCL) has emerged as a representative graph self-supervised method, achieving significant success. The currently prevalent optimization objective for GCL is InfoNCE. Typically, it employs augmentation techniques to obtain two views, where a node in one view acts as the anchor, the corresponding node in the other view serves as the

Chi Li, Yongpeng Zhang, Lidan Lv, Jinchang Liu

Radon is a significant background source in rare event detection experiments. Activated Carbon (AC) adsorption is widely used for effective radon removal. The selection of AC considers its adsorption capacity and radioactive background. In this study, using self-developed devices, we screened and identified a new kind of low-background AC from Qingdao Inaf T

Haoyan Yang, Zhitao Li, Yong Zhang, Jianzong Wang

The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generator formulates the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their advanced QA capabilities, but they are typically too large to

Xingyu Chen, Lemao Liu, Guoping Huang, Zhirui Zhang

Word-Level Auto-Completion (WLAC) plays a crucial role in Computer-Assisted Translation. It aims at providing word-level auto-completion suggestions for human translators. While previous studies have primarily focused on designing complex model architectures, this paper takes a different perspective by rethinking the fundamental question: what kind of words

Yumiharu Nakano

We characterize the Schr\"odinger bridge problems by a family of Mckean-Vlasov stochastic control problems with no terminal time distribution constraint. In doing so, we use the theory of Hilbert space embeddings of probability measures and then describe the constraint as penalty terms defined by the maximum mean discrepancy in the control problems. A sequen

Sean Cottrell, Yuta Hozumi, Guo-Wei Wei

Single-cell RNA sequencing (scRNA-seq) is widely used to reveal heterogeneity in cells, which has given us insights into cell-cell communication, cell differentiation, and differential gene expression. However, analyzing scRNA-seq data is a challenge due to sparsity and the large number of genes involved. Therefore, dimensionality reduction and feature selec

Yating Wu, Ritika Mangla, Greg Durrett, Junyi Jessy Li

Questions Under Discussion (QUD) is a versatile linguistic framework in which discourse progresses as continuously asking questions and answering them. Automatic parsing of a discourse to produce a QUD structure thus entails a complex question generation task: given a document and an answer sentence, generate a question that satisfies linguistic constraints

Hadeel Elayan, Andrew W. Eckford, Raviraj Adve

Folding of proteins into their correct native structure is key to their function. Simultaneously, the intricate interplay between cell movement and protein conformation highlights the complex nature of cellular processes. In this work, we demonstrate the impact of Terahertz (THz) signaling on controlling protein conformational changes in a random medium. Our

Lu Yan, Jiang Hu

The proliferation of science and technology has led to the prevalence of voluminous data sets that are distributed across multiple machines. It is an established fact that conventional statistical methodologies may be unfeasible in the analysis of such massive data sets due to prohibitively long computing durations, memory constraints, communication overhead

Guopeng Li, Liying Tao, Tengfei Zhao

We consider the Cauchy problem for the stochastic Hartree nonlinear wave equations (SHNLW) with a cubic convolution nonlinearity and an additive stochastic forcing on the Euclidean space. Our goal in this paper is two-fold. (i) We study the defocusing energy-critical SHNLW on $\mathbb{R}^d$, for $d \geq 5$, and prove that they are globally well-posed with de

Mahdi Chehimi, Samuel Yen-Chi Chen, Walid Saad, Don Towsley

Quantum federated learning (QFL) is a novel framework that integrates the advantages of classical federated learning (FL) with the computational power of quantum technologies. This includes quantum computing and quantum machine learning (QML), enabling QFL to handle high-dimensional complex data. QFL can be deployed over both classical and quantum communicat

Qi Zhang, Yuran Lu, Yinghui Guo, Yingjie Shang

Fourier ptychography (FP) imaging, drawing on the idea of synthetic aperture, has been demonstrated as a potential approach for remote sub-diffraction-limited imaging. Nevertheless, the farthest imaging distance is still limited around 10 m even though there has been a significant improvement in macroscopic FP. The most severely issue in increasing the imagi

Athul Pradeepkumar Girija

At the far reaches of the outer Solar System, the ice giants remain the last class of planets yet to be studied using orbiters. The 2023-2032 Planetary Science Decadal Survey has underscored the importance of the ice giants in understanding the origin, formation, and evolution of our Solar System. The enormous heliocentric distance of Uranus presents conside

Zihan Zhang, Meng Fang, Fanghua Ye, Ling Chen

Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems. However, collecting a large amount of turn-by-turn annotated dialogue data is costly and inefficient. In this paper, we propose a novel turn-level active learning framework for DST to actively select turns in dialogues to annotate. Given the limited labelling budget, exp

Sheng Xu, Peifeng Li, Qiaoming Zhu

Event coreference resolution (ECR) aims to group event mentions referring to the same real-world event into clusters. Most previous studies adopt the "encoding first, then scoring" framework, making the coreference judgment rely on event encoding. Furthermore, current methods struggle to leverage human-summarized ECR rules, e.g., coreferential events should

Hongyu Ke, Haoxin Wang

Diminished Reality (DR) is considered as the conceptual counterpart to Augmented Reality (AR), and has recently gained increasing attention from both industry and academia. Unlike AR which adds virtual objects to the real world, DR allows users to remove physical content from the real world. When combined with object replacement technology, it presents an fu

Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad

Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves fine-tuning models to make them more adaptable to solving NLP tasks in general. However, it is still uncertain how instruct

Wei Fu, Weihua Du, Jingwei Li, Sunli Chen

In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards while also discovering as many diverse strategies as possible, which can be crucial in many practical applications. Our study examines two design choices for tackling this challenge,

Yingjie Zhu, Jiasheng Si, Yibo Zhao, Haiyang Zhu

Automatic multi-hop fact verification task has gained significant attention in recent years. Despite impressive results, these well-designed models perform poorly on out-of-domain data. One possible solution is to augment the training data with counterfactuals, which are generated by minimally altering the causal features of the original data. However, curre

Jaekwang Kim, Hyung-Jun Park, Aditya Penumarti, Jaejeong Shin

This paper presents a formulation for deterministically calculating optimized paths for a multiagent system consisting of heterogeneous vehicles. The key idea is the calculation of the shortest time for each agent to reach every grid point from its known initial position. Such arrival time map is efficiently computed using the Fast Marching Method (FMM), a c

Ji Youn Lee, Changbeom Shim, Hoa Van Nguyen, Tran Thien Dat Nguyen

Estimating the trajectories of multi-objects poses a significant challenge due to data association ambiguity, which leads to a substantial increase in computational requirements. To address such problems, a divide-and-conquer manner has been employed with parallel computation. In this strategy, distinguished objects that have unique labels are grouped based

Fanfei Meng, Chen-Ao Wang

We propose a novel framework based on the attention mechanism to identify the sentiment of a movie review document. Previous efforts on deep neural networks with attention mechanisms focus on encoder and decoder with fixed numbers of multi-head attention. Therefore, we need a mechanism to stop the attention process automatically if no more useful information

Minkyoung Cho, Yulong Cao, Zixiang Zhou, Z. Morley Mao

Deep neural networks (DNNs) are increasingly integrated into LiDAR (Light Detection and Ranging)-based perception systems for autonomous vehicles (AVs), requiring robust performance under adversarial conditions. We aim to address the challenge of LiDAR spoofing attacks, where attackers inject fake objects into LiDAR data and fool AVs to misinterpret their en

Qi Gou, Zehua Xia, Bowen Yu, Haiyang Yu

Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems. Existing solutions mainly focus on the internal knowledge within the given passage or the semantic word space for diverse content planning. These methods, however, have not consider

Jacob Cornejo, Kathryn McCormick

We classify certain algebras of matrix-valued cross-sections over an annulus up to complete isometric isomorphism, based on topological bundle invariants. In particular, we study sections of matrix bundles which are continuous on the closure of the annulus and holomorphic on its interior. Our strategy includes exploiting the relationship between concomitants

Kiril Bangachev, Guy Bresler

In this paper we study the random geometric graph $\mathsf{RGG}(n,\mathbb{T}^d,\mathsf{Unif},\sigma^q_p,p)$ with $L_q$ distance where each vertex is sampled uniformly from the $d$-dimensional torus and where the connection radius is chosen so that the marginal edge probability is $p$. In addition to results addressing other questions, we make progress on det

Sanghoon Rho, Philipp Martens, Seungcheol Shin, Yeoneo Kim

Coyote C++ is an automated testing tool that uses a sophisticated concolic-execution-based approach to realize fully automated unit testing for C and C++. While concolic testing has proven effective for languages such as C and Java, tools have struggled to achieve a practical level of automation for C++ due to its many syntactical intricacies and overall com

Jiahui Zhang

Stimulated Raman Adiabatic Passage (STIRAP) and its variants, such as multi-state chainwise-STIRAP allow efficiently transferring the populations in multi-state system and have been widely used to prepare ultracold deeply-bound molecules. However, their transfer efficiencies are generally imperfect. The main obstacle is the presence of losses and the require

Zhongzhou Chen, Emily Frederick, Colleen Cui, Munaimah Khan

This paper explores using large isomorphic problem banks to overcome many challenges of traditional exams in large STEM classes, especially the threat of content sharing websites and generative AI to the security of exam items. We first introduce an efficient procedure for creating large numbers of isomorphic physics problems, assisted by the large language

Sopam Dasgupta, Farhad Shakerin, Joaquín Arias, Elmer Salazar

Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they are unable to reveal how they reach these prediction decisions. A need for transparency demands justification for such prediction

Mengxi Chen, Jiangchao Yao, Linyu Xing, Yu Wang

Multimodal models trained on complete modality data often exhibit a substantial decrease in performance when faced with imperfect data containing corruptions or missing modalities. To address this robustness challenge, prior methods have explored various approaches from aspects of augmentation, consistency or uncertainty, but these approaches come with assoc

Justin Payan, Swaroop Mishra, Mukul Singh, Carina Negreanu

With the evolution of Large Language Models (LLMs) we can solve increasingly more complex NLP tasks across various domains, including spreadsheets. This work investigates whether LLMs can generate code (Excel OfficeScripts, a TypeScript API for executing many tasks in Excel) that solves Excel specific tasks provided via natural language user instructions. To

Gregory Mohammed

To investigate the physical nature of neutrino-heating on the result of a 1-dimensional core-collapse supernova. Colgate were the first to suggest that neutrinos may play a crucial role in core collapse supernova by taking up gravitational binding energy from the core and depositing it in the rest of the star. The fluid is contained in a shock tube in a regi

Rei Inoue, Atsuo Kuniba, Yuji Terashima

We construct a new solution to the tetrahedron equation and the three-dimensional (3D) reflection equation by extending the quantum cluster algebra approach by Sun and Yagi concerning the former. We consider the Fock-Goncharov quivers associated with the longest elements of the Weyl groups of type $A$ and $C$, and investigate the cluster transformations corr

Nicholas Ramirez, Michael Burgess

Rock skipping is a highly dynamic and relatively complex task that can easily be performed by humans. This project aims to bring rock skipping into a robotic setting, utilizing the lessons we learned in Robotic Manipulation. Specifically, this project implements a system consisting of a robotic arm and dynamic environment to perform rock skipping in simulati

Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo

Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheating with answers memorized from pretraining corpus, or, via a multi-step reasoning mechanism. In this paper, we try to answer this question by exploring a mechanistic interpretation

Muhammad Hassan, Mahnoor Jameel, Tian Wang, Masooda Bashir

FemTech or Female Technology, is an expanding field dedicated to providing affordable and accessible healthcare solutions for women, prominently through Female Health Applications that monitor health and reproductive data. With the leading app exceeding 1 billion downloads, these applications are gaining widespread popularity. However, amidst contemporary ch

Yuan Li, Huan Liu, Yubo Tao, Xiangyang He

Recently, deep learning-based tooth segmentation methods have been limited by the expensive and time-consuming processes of data collection and labeling. Achieving high-precision segmentation with limited datasets is critical. A viable solution to this entails fine-tuning pre-trained multiview-based models, thereby enhancing performance with limited data. Ho

Qingli Liao, Junzhi Wang, Peng Xie, Enwei Liang

The density functional theory (DFT) is the most versatile electronic structure method used in quantum chemical calculations, and is increasingly applied in astrochemical research. This mini-review provides an overview of the applications of DFT calculations in understanding the chemistry that occurs in star-forming regions. We survey investigations into the

Yiying Yang, Wen Liu, Fukun Yin, Xin Chen

Recent advancements in implicit neural representations have contributed to high-fidelity surface reconstruction and photorealistic novel view synthesis. However, the computational complexity inherent in these methodologies presents a substantial impediment, constraining the attainable frame rates and resolutions in practical applications. In response to this

Nishant Balepur, Jie Huang, Kevin Chen-Chuan Chang

Text style transfer is a prominent task that aims to control the style of text without inherently changing its factual content. To cover more text modification applications, such as adapting past news for current events and repurposing educational materials, we propose the task of text fact transfer, which seeks to transfer the factual content of a source te

Junfei Li, Simon X. Yang

Intelligent escape is an interdisciplinary field that employs artificial intelligence (AI) techniques to enable robots with the capacity to intelligently react to potential dangers in dynamic, intricate, and unpredictable scenarios. As the emphasis on safety becomes increasingly paramount and advancements in robotic technologies continue to advance, a wide r

Sandeep Banik, Shaunak D. Bopardikar

We introduce FlipDyn with control, a finite-horizon zero-sum resource takeover game, where a defender and an adversary decide when to takeover and how to control a common resource. At each discrete-time step, the players can take over or retain control, incurring state and control-dependent costs. The system is modeled as a hybrid dynamical system, with a di

Yu Zhang, Yanzhen Shen, SeongKu Kang, Xiusi Chen

With the rapid increase in paper submissions to academic conferences, the need for automated and accurate paper-reviewer matching is more critical than ever. Previous efforts in this area have considered various factors to assess the relevance of a reviewer's expertise to a paper, such as the semantic similarity, shared topics, and citation connections betwe

Nimita Shinde, Vishnu Narayanan, James Saunderson

In this paper, we consider Frank-Wolfe-based algorithms for composite convex optimization problems with objective involving a logarithmically-homogeneous, self-concordant functions. Recent Frank-Wolfe-based methods for this class of problems assume an oracle that returns exact solutions of a linearized subproblem. We relax this assumption and propose a varia

Jun Hu, Bryan Hooi, Bingsheng He

Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Typical HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors, enabl

Weimin Lyu, Songzhu Zheng, Lu Pang, Haibin Ling

Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights. In this paper, we directly

Rongsheng Wang, Qi Li, Sihong Xie

General large language models (LLMs) such as ChatGPT have shown remarkable success, but it has also raised concerns among people about the misuse of AI-generated texts. Therefore, an important question is how to detect whether the texts are generated by ChatGPT or by humans. Existing detectors are built on the assumption that there is a distribution gap betw

Zekun Li, Wenxuan Zhou, Yao-Yi Chiang, Muhao Chen

Humans subconsciously engage in geospatial reasoning when reading articles. We recognize place names and their spatial relations in text and mentally associate them with their physical locations on Earth. Although pretrained language models can mimic this cognitive process using linguistic context, they do not utilize valuable geospatial information in large

Seok-Jun Chang, Nicole Arulanantham, Max Gronke, Gregory J. Herczeg

Lyman-$\alpha$ (Ly$\alpha$) is the strongest emission line in the accretion-generated UV spectra from T-Tauri stars and, as such, plays a critical role in regulating chemistry within the surrounding protoplanetary disks. Due to its resonant nature, the scattering of Ly$\alpha$ photons along the line-of-sight encodes information about the physical properties