May 2023 arXiv papers — page 58

Joel Jiahao Fan, Zhe-Yu Jeff Ou, Zhedong Zhang

Quantum entanglement has emerged as a great resource for interactions between molecules and radiation. We propose a new paradigm of stimulated Raman scattering with entangled photons. A quantum ultrafast Raman spectroscopy is developed for condensed-phase molecules, to monitor the exciton populations and coherences. Analytic results are obtained, showing a t

Anna Martin-Boyle, Andrew Head, Kyle Lo, Risham Sidhu

Mathematical symbol definition extraction is important for improving scholarly reading interfaces and scholarly information extraction (IE). However, the task poses several challenges: math symbols are difficult to process as they are not composed of natural language morphemes; and scholarly papers often contain sentences that require resolving complex coord

Ishani Mondal, Michelle Yuan, Anandhavelu N, Aparna Garimella

Learning template based information extraction from documents is a crucial yet difficult task. Prior template-based IE approaches assume foreknowledge of the domain templates; however, real-world IE do not have pre-defined schemas and it is a figure-out-as you go phenomena. To quickly bootstrap templates in a real-world setting, we need to induce template sl

Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang

LLMs (large language models) such as ChatGPT have shown remarkable language understanding and generation capabilities. Although reference-free evaluators based on LLMs show better human alignment than traditional reference-based evaluators, there are many challenges in using reference-free evaluators based on LLMs. Reference-free evaluators are more suitable

Yiduo Guo, Bing Liu, Dongyan Zhao

Existing continual learning (CL) research regards catastrophic forgetting (CF) as almost the only challenge. This paper argues for another challenge in class-incremental learning (CIL), which we call cross-task class discrimination (CTCD),~i.e., how to establish decision boundaries between the classes of the new task and old tasks with no (or limited) access

Yilong Xu, Yang Liu, Hao Sun

In nature, the behaviors of many complex systems can be described by parsimonious math equations. Automatically distilling these equations from limited data is cast as a symbolic regression process which hitherto remains a grand challenge. Keen efforts in recent years have been placed on tackling this issue and demonstrated success in symbolic regression. Ho

Yu Ling, Weimin Tan, Bo Yan

Survival analysis aims at modeling the relationship between covariates and event occurrence with some untracked (censored) samples. In implementation, existing methods model the survival distribution with strong assumptions or in a discrete time space for likelihood estimation with censorship, which leads to weak generalization. In this paper, we propose Imp

Ken Caluwaerts, Atil Iscen, J. Chase Kew, Wenhao Yu

Animals have evolved various agile locomotion strategies, such as sprinting, leaping, and jumping. There is a growing interest in developing legged robots that move like their biological counterparts and show various agile skills to navigate complex environments quickly. Despite the interest, the field lacks systematic benchmarks to measure the performance o

João M. Souto-Maior

Social scientists increasingly use the concept of opportunity hoarding to explain the formation of Black-White educational inequalities. However, this concept is often loosely defined, leading to varied interpretations of the inequality-producing mechanisms it captures. To bring clarity to this valuable sociological concept, this theoretical paper, informed

Shaoxiang Wu, Damai Dai, Ziwei Qin, Tianyu Liu

Video multimodal fusion aims to integrate multimodal signals in videos, such as visual, audio and text, to make a complementary prediction with multiple modalities contents. However, unlike other image-text multimodal tasks, video has longer multimodal sequences with more redundancy and noise in both visual and audio modalities. Prior denoising methods like

Lingbing Guo, Zhuo Chen, Jiaoyan Chen, Yin Fang

Recent embedding-based methods have achieved great successes in exploiting entity alignment from knowledge graph (KG) embeddings of multiple modalities. In this paper, we study embedding-based entity alignment (EEA) from a perspective of generative models. We show that EEA shares similarities with typical generative models and prove the effectiveness of the

Yuri S. Ribeiro, Fazal E-Asim, André L. F de Almeida, Behrooz Makki

In this letter, we consider an intelligent reflecting surface (IRS)-assisted multiple input multiple output (MIMO) communication and we optimize the joint active and passive beamforming by exploiting the geometrical structure of the propagation channels. Due to the inherent Kronecker product structure of the channel matrix, the global beamforming optimizatio

Yushu Chen, Shengzhuo Liu, Jinzhe Yang, Hao Jing

In order to enhance the performance of Transformer models for long-term multivariate forecasting while minimizing computational demands, this paper introduces the Joint Time-Frequency Domain Transformer (JTFT). JTFT combines time and frequency domain representations to make predictions. The frequency domain representation efficiently extracts multi-scale dep

James M. Etheridge, Joseph Dill, Connor P. Dempsey, Mihir Pendharkar

We report on the interplay of two uniaxial magnetic anisotropies in epitaxial Fe thin films of varying thickness grown on InAs(001) as observed in ferromagnetic resonance experiments. One anisotropy originates from the Fe/InAs interface while the other originates from in-plane shear strain resulting from the anisotropic relaxation of the Fe film. X-ray diffr

Qi Zeng, Mankeerat Sidhu, Ansel Blume, Hou Pong Chan

Opinions in scientific research papers can be divergent, leading to controversies among reviewers. However, most existing datasets for opinion summarization are centered around product reviews and assume that the analyzed opinions are non-controversial, failing to account for the variability seen in other contexts such as academic papers, political debates,

Wuhyun Sohn, James R. Fergusson, E. P. S. Shellard

We present a new independent pipeline for the CMB bispectrum estimation of primordial non-Gaussianity and release a public code for constraining bispectrum shapes of interest based on the Planck 2018 temperature and polarization data. The estimator combines the strengths of the conventional KSW and Modal estimators at the cost of increased computational comp

Xiaochu Li, Minqian Liu, Zhiyang Xu, Lifu Huang

Biomedical entity linking and event extraction are two crucial tasks to support text understanding and retrieval in the biomedical domain. These two tasks intrinsically benefit each other: entity linking disambiguates the biomedical concepts by referring to external knowledge bases and the domain knowledge further provides additional clues to understand and

Hemanth Manjunatha, Andrey Pak, Dimitar Filev, Panagiotis Tsiotras

Autonomous driving has received a great deal of attention in the automotive industry and is often seen as the future of transportation. The development of autonomous driving technology has been greatly accelerated by the growth of end-to-end machine learning techniques that have been successfully used for perception, planning, and control tasks. An important

Manabu Tsujimoto, Kaveh Delfanazari, Takanari Kashiwagi, Toshiaki Hattori

Compared with adjacent microwaves and infrared frequencies, terahertz (THz) frequency offers numerous advantages for imaging applications. The unique THz spectral signatures of chemicals allow the development of THz imaging systems for nondestructive tests and the evaluation of biological objects, materials, components, circuits, and systems, which are espec

Lingbing Guo, Weiqing Wang, Zhuo Chen, Ningyu Zhang

Reasoning system dynamics is one of the most important analytical approaches for many scientific studies. With the initial state of a system as input, the recent graph neural networks (GNNs)-based methods are capable of predicting the future state distant in time with high accuracy. Although these methods have diverse designs in modeling the coordinates and

Zhe Wang, ZhiJie He, Ding Liu

The article introduces a new method for applying Quantum Clustering to graph structures. Quantum Clustering (QC) is a novel density-based unsupervised learning method that determines cluster centers by constructing a potential function. In this method, we use the Graph Gradient Descent algorithm to find the centers of clusters. GPU parallelization is utilize

Simin Keykhosravi, Ebrahim Bedeer

Being capable of enhancing the spectral efficiency (SE), faster-than-Nyquist (FTN) signaling is a promising approach for wireless communication systems. This paper investigates the doubly-selective (i.e., time- and frequency-selective) channel estimation and data detection of FTN signaling. We consider the intersymbol interference (ISI) resulting from both t

Ruizhe Chen, Sanjib Basu, Qian Shi

Restricted mean survival time (RMST) is an intuitive summary statistic for time-to-event random variables, and can be used for measuring treatment effects. Compared to hazard ratio, its estimation procedure is robust against the non-proportional hazards assumption. We propose nonparametric Bayeisan (BNP) estimators for RMST using a dependent stick-breaking p

Nikolay Yegovtsev, Victor Gurarie

We study the motion of a heavy impurity immersed in a weakly interacting BEC using the Gross-Pitaevskii equation (GPe). We construct a perturbative solution to the GPe in powers of impurity velocity in the case when the boson-impurity potential is tuned to unitarity and calculate the effective mass of the polaron. In addition, we calculate the interaction en

Davit Soselia, Khalid Saifullah, Tianyi Zhou

Automated reverse engineering of HTML/CSS code from UI screenshots is an important yet challenging problem with broad applications in website development and design. In this paper, we propose a novel vision-code transformer (ViCT) composed of a vision encoder processing the screenshots and a language decoder to generate the code. They are initialized by pre-

Jack H. Koolen, Mamoon Abdullah, Brhane Gebremichel, Sakander Hayat

In this paper, we study the $q$-distance matrix for a distance-regular graph and show that the $q$-distance matrix of a distance-regular graph with classical parameters ($D, q, \alpha, \beta$) has exactly three distinct eigenvalues, of which one is zero. Moreover, we study distance-regular graphs whose $q$-distance matrix has exactly one positive eigenvalue.

Yan Zhou, Qingkai Fang, Yang Feng

End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language. As a cross-modal task, end-to-end ST is difficult to train with limited data. Existing methods often try to transfer knowledge from machine translation (MT), but their performances are restricted by the modality gap between sp

Prashant Singh, Manoj K Harbola

This article is part-I of a review of density-functional theory (DFT) that is the most widely used method for calculating electronic structure of materials. The accuracy and ease of numerical implementation of DFT methods has resulted in its extensive use for materials design and discovery and has thus ushered in the new field of computational material scien

Weideng Cui, Li Luo, Zheming Xu

We prove that the q-Schur algebras of finite type introduced in [LW22] are cellular in the sense of Graham and Lehrer, which is a generalization of Geck's theorem on the cellularity of Hecke algebras of finite type. Moreover, we study special modules of the associated asymptotic Schur algebras and left cell representations of Schur algebras, which generalize

Rishi Sonthalia, Anna Seigal, Guido Montufar

We define the supermodular rank of a function on a lattice. This is the smallest number of terms needed to decompose it into a sum of supermodular functions. The supermodular summands are defined with respect to different partial orders. We characterize the maximum possible value of the supermodular rank and describe the functions with fixed supermodular ran

BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson

The spin and parity of the charmed mesons $D_{s}^{*+}$, $D^{*0}$ and $D^{*+}$ are determined for the first time to be $J^P=1^{-}$ with significances greater than 10$\sigma$ over other hypotheses of $2^{+}$ and $3^{-}$, using an $e^+e^-$ collision data sample with an integrated luminosity of 3.19 fb$^{-1}$ collected by the BESIII detector at a center-of-mass

Xiang Zhang, Senyu Li, Bradley Hauer, Ning Shi

Large Language Models (LLMs) have demonstrated exceptional natural language understanding abilities and have excelled in a variety of natural language processing (NLP)tasks in recent years. Despite the fact that most LLMs are trained predominantly in English, multiple studies have demonstrated their comparative performance in many other languages. However, f

Sam Musker, Ellie Pavlick

Large Language Models (LLMs) have driven extraordinary improvements in NLP. However, it is unclear how such models represent lexical concepts-i.e., the meanings of the words they use. This paper evaluates the lexical representations of GPT-3 and GPT-4 through the lens of HIPE theory, a theory of concept representations which focuses on representations of wor

Zhesi Shen, Liying Yang, Jinshan Wu

Two journal-level indicators, respectively the mean ($m^i$) and the standard deviation ($v^i$) are proposed to be the core indicators of each journal and we show that quite several other indicators can be calculated from those two core indicators, assuming that yearly citation counts of papers in each journal follows more or less a log-normal distribution. T

Chenglei Si, Weijia Shi, Chen Zhao, Luke Zettlemoyer

While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical evidence that state-of-the-art LLMs suffer from poor generalizability on reasoning types beyond those seen in the prompt. To

Tianyu Gao, Howard Yen, Jiatong Yu, Danqi Chen

Large language models (LLMs) have emerged as a widely-used tool for information seeking, but their generated outputs are prone to hallucination. In this work, our aim is to allow LLMs to generate text with citations, improving their factual correctness and verifiability. Existing work mainly relies on commercial search engines and human evaluation, making it

Francesco Costantino, Nathan Geer, Bertrand Patureau-Mirand, Alexis Virelizier

Chromatic maps for spherical tensor categories are instrumental tools to construct (non semisimple) invariants of 3-manifolds and their extension to (non compact) (2+1)-TQFTs. In this paper, we introduce left and right chromatic maps for finite tensor categories and prove that such maps always exist. As a corollary, we obtain that any spherical finite tensor

Shufan Wang, Yixiao Song, Andrew Drozdov, Aparna Garimella

In this paper, we study the generation quality of interpolation-based retrieval-augmented language models (LMs). These methods, best exemplified by the KNN-LM, interpolate the LM's predicted distribution of the next word with a distribution formed from the most relevant retrievals for a given prefix. While the KNN-LM and related methods yield impressive decr

Ashish Kumar, Prashant Singh, Manoj K. Harbola

This is the second and the final part of the review on density functional theory (DFT), referred to as DFT-II. In the first review, DFT-I, we have discussed wavefunction-based methods, their complexity, and the basic of density functional theory. In DFT-II, we focus on fundamentals of DFT and their implications for the betterment of the theory. We start our

Miaoran Li, Baolin Peng, Michel Galley, Jianfeng Gao

Fact-checking is an essential task in NLP that is commonly utilized for validating the factual accuracy of claims. Prior work has mainly focused on fine-tuning pre-trained languages models on specific datasets, which can be computationally intensive and time-consuming. With the rapid development of large language models (LLMs), such as ChatGPT and GPT-3, res

Debaditya Shome, Kuldeep Yadav

Large pre-trained language models (PLMs) have made significant progress in encoding world knowledge and spawned a new set of learning paradigms including zero-shot, few-shot, and in-context learning. Many language tasks can be modeled as a set of prompts (for example, is this text about geography?) and language models can provide binary answers, i.e., Yes or

Setareh Dabiri, Vasileios Lioutas, Berend Zwartsenberg, Yunpeng Liu

When training object detection models on synthetic data, it is important to make the distribution of synthetic data as close as possible to the distribution of real data. We investigate specifically the impact of object placement distribution, keeping all other aspects of synthetic data fixed. Our experiment, training a 3D vehicle detection model in CARLA an

ChongYang Liu, XiaoMin Shen, Bin Zhou, Jun Gao

We present FMNLO, a framework to combine general-purpose Monte Carlo generators and fragmentation functions (FFs). It is based on a hybrid scheme of phase-space slicing method and local subtraction method, and accurate to next-to-leading order (NLO) in QCD. The new framework has been interfaced to MG5 aMC@NLO and made publicly available in this work. We demo

Satoru Hayami, Ryota Yambe

We investigate the instability toward a skyrmion crystal (SkX) in noncentrosymmetric cubic magnets with an emphasis on a comparison between point groups $(O,T)$ and $T_{\rm d}$. By constructing low-temperature magnetic phase diagrams under an external magnetic field for three directions based on numerically simulated annealing, we find that the system under

Wenting Zhao, Justin T. Chiu, Claire Cardie, Alexander M. Rush

Abductive reasoning aims to find plausible explanations for an event. This style of reasoning is critical for commonsense tasks where there are often multiple plausible explanations. Existing approaches for abductive reasoning in natural language processing (NLP) often rely on manually generated annotations for supervision; however, such annotations can be s

Sahithya Ravi, Raymond Ng, Vered Shwartz

Understanding the speaker's intended meaning often involves drawing commonsense inferences to reason about what is not stated explicitly. In multi-event sentences, it requires understanding the relationships between events based on contextual knowledge. We propose COMET-M (Multi-Event), an event-centric commonsense model capable of generating commonsense inf

Pin-Er Chen, Po-Ya Angela Wang, Hsin-Yu Chou, Yu-Hsiang Tseng

This paper explores the grounding issue regarding multimodal semantic representation from a computational cognitive-linguistic view. We annotate images from the Flickr30k dataset with five perceptual properties: Affordance, Perceptual Salience, Object Number, Gaze Cueing, and Ecological Niche Association (ENA), and examine their association with textual elem

Ki-Ahm Lee, Hyungsung Yun

In this paper, we establish the boundary regularity results for viscosity solutions of fully nonlinear degenerate/singular parabolic equations of the form $$u_t - x_n^{\gamma} F(D^2 u,x,t) = f,$$ where $\gamma<1$. These equations are motivated by the porous media type equations. We show the boundary $C^{1,\alpha}$-regularity of functions in their solutions c

Joseph M. Hellerstein, Shadaj Laddad, Mae Milano, Conor Power

In the Hydro project we are designing a compiler toolkit that can optimize for the concerns of distributed systems, including scale-up and scale-down, availability, and consistency of outcomes across replicas. This invited paper overviews the project, and provides an early walk-through of the kind of optimization that is possible. We illustrate how type tran

Jeremy R. Cole, Michael J. Q. Zhang, Daniel Gillick, Julian Martin Eisenschlos

Trustworthy language models should abstain from answering questions when they do not know the answer. However, the answer to a question can be unknown for a variety of reasons. Prior research has focused on the case in which the question is clear and the answer is unambiguous but possibly unknown, but the answer to a question can also be unclear due to uncer

Ziyu Gong, Xiong Zhao, Chen Yang

This paper aims to detect the potential injury risk of the anterior cruciate ligament (ACL) by proposing an ACL potential injury risk assessment algorithm based on key points of the human body detected using computer vision technology. To obtain the key points data of the human body in each frame, OpenPose, an open source computer vision algorithm, was emplo

Jikun Kang, Romain Laroche, Xingdi Yuan, Adam Trischler

Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. As a result, training on a new task m

Mulong Xie, Jiaming Ye, Zhenchang Xing, Lei Ma

To ensure app compatibility and smoothness of user experience across diverse devices and platforms, developers have to perform cross-device, cross-platform testing of their apps, which is laborious. There comes a recently increasing trend of using a record and replay approach to facilitate the testing process. However, the graphic user interface (GUI) of an

Bryan Li, Samar Haider, Chris Callison-Burch

Do the Spratly Islands belong to China, the Philippines, or Vietnam? A pretrained large language model (LLM) may answer differently if asked in the languages of each claimant country: Chinese, Tagalog, or Vietnamese. This contrasts with a multilingual human, who would likely answer consistently. In this paper, we show that LLMs recall certain geographical kn

Yiming Chen, Sihui Wang, Dong Xu

Background Atrial fibrillation is often missed by traditional intermittent electrocardiogram monitoring after ischemic stroke due to its paroxysmal and asymptomatic nature. The knowledge of the unique characteristics of the population with atrial fibrillation detected after stroke (AFDAS) enables more ischemic stroke patients to benefit from more aggressive

Feiyang Wu, Jingyang Ke, Anqi Wu

We study the problem of Inverse Reinforcement Learning (IRL) with an average-reward criterion. The goal is to recover an unknown policy and a reward function when the agent only has samples of states and actions from an experienced agent. Previous IRL methods assume that the expert is trained in a discounted environment, and the discount factor is known. Thi

Aayushya Agarwal, Larry Pileggi

Distributed optimization is an essential paradigm to solve large-scale optimization problems in modern applications where big-data and high-dimensionality creates a computational bottleneck. Distributed optimization algorithms that exhibit fast convergence allow us to fully utilize computing resources and effectively scale to larger optimization problems in

James Schmidt

Empirical risk minimization stands behind most optimization in supervised machine learning. Under this scheme, labeled data is used to approximate an expected cost (risk), and a learning algorithm updates model-defining parameters in search of an empirical risk minimizer, with the aim of thereby approximately minimizing expected cost. Parameter update is oft

Francisco Rodríguez

This article reviews recent advances in addressing empirical identification issues in cross-country and country-level studies and their implications for the identification of the effectiveness and consequences of economic sanctions. I argue that, given the difficulties in assessing causal relationships in cross-national data, country-level case studies can s

Jason Milionis, Ciamac C. Moallemi, Tim Roughgarden

We consider the impact of trading fees on the profits of arbitrageurs trading against an automated market maker (AMM) or, equivalently, on the adverse selection incurred by liquidity providers (LPs) due to arbitrage. We extend the model of Milionis et al. [2022] for a general class of two asset AMMs to introduce both fees and discrete Poisson block generatio

Li Zhang, Hainiu Xu, Abhinav Kommula, Chris Callison-Burch

Much text describes a changing world (e.g., procedures, stories, newswires), and understanding them requires tracking how entities change. An earlier dataset, OpenPI, provided crowdsourced annotations of entity state changes in text. However, a major limitation was that those annotations were free-form and did not identify salient changes, hampering model ev

Siddhartha Sarkar, Mohamed El Hedi Bahri, Andrej Košmrlj

We investigate the effect of thermal fluctuations on the mechanical properties of nanotubes by employing tools from statistical physics. For 2D sheets it was previously shown that thermal fluctuations effectively renormalize elastic moduli beyond a characteristic temperature-dependent thermal length scale (a few nanometers for graphene at room temperature),

Chiyoung Song, Dongjae Lee

The size of training dataset is known to be among the most dominating aspects of training high-performance face recognition embedding model. Building a large dataset from scratch could be cumbersome and time-intensive, while combining multiple already-built datasets poses the risk of introducing large amount of label noise. We present a novel training method

Tao Li, Ghazaleh Kazeminejad, Susan W. Brown, Martha Palmer

Semantic role labeling (SRL) has multiple disjoint label sets, e.g., VerbNet and PropBank. Creating these datasets is challenging, therefore a natural question is how to use each one to help the other. Prior work has shown that cross-task interaction helps, but only explored multitask learning so far. A common issue with multi-task setup is that argument seq

James Y. Huang, Wenlin Yao, Kaiqiang Song, Hongming Zhang

Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be interpreted via compositional operations such as sentence fusion or difference. It is unclear whether the compositional semantics

Yutong Zhou, Nobutaka Shimada

Text-to-image generation has attracted significant interest from researchers and practitioners in recent years due to its widespread and diverse applications across various industries. Despite the progress made in the domain of vision and language research, the existing literature remains relatively limited, particularly with regard to advancements and appli

Yiwen Ding, Jiarui Liu, Zhiheng Lyu, Kun Zhang

While several previous studies have analyzed gender bias in research, we are still missing a comprehensive analysis of gender differences in the AI community, covering diverse topics and different development trends. Using the AI Scholar dataset of 78K researchers in the field of AI, we identify several gender differences: (1) Although female researchers ten

Sarah Wiegreffe, Matthew Finlayson, Oyvind Tafjord, Peter Clark

When pretrained language models (LMs) are applied to discriminative tasks such as multiple-choice questions, they place probability mass on vocabulary tokens that aren't among the given answer choices. Spreading probability mass across multiple surface forms with identical meaning (such as "bath" and "bathtub") is thought to cause an underestimation of a mod

Serena Wang, Stephen Bates, P. M. Aronow, Michael I. Jordan

From the social sciences to machine learning, it has been well documented that metrics to be optimized are not always aligned with social welfare. In healthcare, Dranove et al. (2003) showed that publishing surgery mortality metrics actually harmed the welfare of sicker patients by increasing provider selection behavior. We analyze the incentive misalignment

Joseph D. Viviano, Omar G. Younis, Sanghyeok Choi, Victor Schmidt

The growing popularity of generative flow networks (GFlowNets or GFNs) from a range of researchers with diverse backgrounds and areas of expertise necessitates a library that facilitates the testing of new features (e.g., training losses and training policies) against standard benchmark implementations, or on a set of common environments. We present torchgfn

Yuling Yao, Justin Domke

To check the accuracy of Bayesian computations, it is common to use rank-based simulation-based calibration (SBC). However, SBC has drawbacks: The test statistic is somewhat ad-hoc, interactions are difficult to examine, multiple testing is a challenge, and the resulting p-value is not a divergence metric. We propose to replace the marginal rank test with a

Ruohao Guo, Wei Xu, Alan Ritter

Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this challenge, we investigate whether LLMs can be meta-trained based on representative lexicons to recognize new styles the

Kexun Zhang, Danqing Wang, Jingtao Xia, William Yang Wang

Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems that require not only implementation but also identification of the suitable algorithm. Moreover, LLM-generated programs lack guaranteed correctness and require human verification. To address these challenges, we propose ALGO, a fram

Pritika Ramu, Sijia Wang, Lalla Mouatadid, Joy Rimchala

Current research in form understanding predominantly relies on large pre-trained language models, necessitating extensive data for pre-training. However, the importance of layout structure (i.e., the spatial relationship between the entity blocks in the visually rich document) to relation extraction has been overlooked. In this paper, we propose REgion-Aware

Ella Ivanova, Georgii Kalagov, Marina Komarova, Mikhail Nalimov

The quantum-field renormalization group method is one of the most efficient and powerful tools for studying critical and scaling phenomena in interacting many-particle systems. The multiloop Feynman diagrams underpin the specific implementation of the renormalization group program. In recent years, multiloop computation has had a significant breakthrough in

Ryosuke Omori, Koichi Ito, Shunsuke Kanemitsu, Ryusuke Kimura

Modelling host behavioral change in response to epidemics is important to describe disease dynamics and many previous studies proposed mathematical models describing it. Indeed, the epidemic of COVID-19 clearly demonstrated that people changed their activity in response to the epidemic, which subsequently modified the disease dynamics. To predict the behavio

Xiaofeng Liu, Jerry L. Prince, Fangxu Xing, Jiachen Zhuo

Self-training is an important class of unsupervised domain adaptation (UDA) approaches that are used to mitigate the problem of domain shift, when applying knowledge learned from a labeled source domain to unlabeled and heterogeneous target domains. While self-training-based UDA has shown considerable promise on discriminative tasks, including classification

Sebastian Cadavid-Sanchez, Khalil Kacem, Rafael Aparecido Martins Frade, Johannes Boehm

To study social, economic, and historical questions, researchers in the social sciences and humanities have started to use increasingly large unstructured textual datasets. While recent advances in NLP provide many tools to efficiently process such data, most existing approaches rely on generic solutions whose performance and suitability for domain-specific

Hamed Rahimi, Jacob Louis Hoover, David Mimno, Hubert Naacke

The recent explosion in work on neural topic modeling has been criticized for optimizing automated topic evaluation metrics at the expense of actual meaningful topic identification. But human annotation remains expensive and time-consuming. We propose LLM-based methods inspired by standard human topic evaluations, in a family of metrics called Contextualized

Kangkang Duan, Christine Wun Ki Suen, Zhengbo Zou

Letting robots emulate human behavior has always posed a challenge, particularly in scenarios involving multiple robots. In this paper, we presented a framework aimed at achieving multi-agent reinforcement learning for robot control in construction tasks. The construction industry often necessitates complex interactions and coordination among multiple robots

Andrew Engel, Zhichao Wang, Natalie S. Frank, Ioana Dumitriu

A recent trend in explainable AI research has focused on surrogate modeling, where neural networks are approximated as simpler ML algorithms such as kernel machines. A second trend has been to utilize kernel functions in various explain-by-example or data attribution tasks. In this work, we combine these two trends to analyze approximate empirical neural tan

Kangkang Duan, Zhengbo Zou

Construction robots are challenging the traditional paradigm of labor intensive and repetitive construction tasks. Present concerns regarding construction robots are focused on their abilities in performing complex tasks consisting of several subtasks and their adaptability to work in unstructured and dynamic construction environments. Imitation learning (IL

Alexander Hoyle, Rupak Sarkar, Pranav Goel, Philip Resnik

When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been

Ziqi Zhao, Yucheng Shi, Shushan Wu, Fan Yang

Deep learning models developed for time-series associated tasks have become more widely researched nowadays. However, due to the unintuitive nature of time-series data, the interpretability problem -- where we understand what is under the hood of these models -- becomes crucial. The advancement of similar studies in computer vision has given rise to many pos

Smrithan Ravichandran, Marine Huault, Roberto Lera, Calvin Z. He

We present a novel technique to assess the focal volume of petawatt-class lasers at full power. Our approach exploits quantitative measurement of the angular distribution of electrons born in the focus via ionization of rarefied gas, which are accelerated forward and ejected ponderomotively by the field. We show that a bivariate ($\theta, \phi$) angular dist

Lucas Rafael Stefanel Gris, Ricardo Marcacini, Arnaldo Candido Junior, Edresson Casanova

Automatic speech recognition (ASR) systems play a key role in applications involving human-machine interactions. Despite their importance, ASR models for the Portuguese language proposed in the last decade have limitations in relation to the correct identification of punctuation marks in automatic transcriptions, which hinder the use of transcriptions by oth

Xiwen Li, Tristalee Mangin, Surojit Saha, Evan Blanchard

Combustion vehicle emissions contribute to poor air quality and release greenhouse gases into the atmosphere, and vehicle pollution has been associated with numerous adverse health effects. Roadways with extensive waiting and/or passenger drop off, such as schools and hospital drop-off zones, can result in high incidence and density of idling vehicles. This

Margarita Bugueño, Gerard de Melo

Given the success of Graph Neural Networks (GNNs) for structure-aware machine learning, many studies have explored their use for text classification, but mostly in specific domains with limited data characteristics. Moreover, some strategies prior to GNNs relied on graph mining and classical machine learning, making it difficult to assess their effectiveness

Alex Wilf, Syeda Nahida Akter, Leena Mathur, Paul Pu Liang

The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition that deciding what to mask can substantially improve learning outcomes. We investigate this in continued pretraining setting in which pretrained models

Josip Jukić, Jan Šnajder

Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques, particularly in low-resource domains and languages. Active learning (AL), a set of algorithms designed to decrease labeling costs by minimizing label complexity, has shown promise in confronting the labeling bottleneck. In parallel, adapter modules designe

Abhineet Singh, Ila Jasra, Omar Mouhammed, Nidheesh Dadheech

This paper presents advancements in automated early-stage prediction of the success of reprogramming human induced pluripotent stem cells (iPSCs) as a potential source for regenerative cell therapies.The minuscule success rate of iPSC-reprogramming of around $ 0.01% $ to $ 0.1% $ makes it labor-intensive, time-consuming, and exorbitantly expensive to generat

Erin George, Joyce Chew, Deanna Needell

Societal biases in the usage of words, including harmful stereotypes, are frequently learned by common word embedding methods. These biases manifest not only between a word and an explicit marker of its stereotype, but also between words that share related stereotypes. This latter phenomenon, sometimes called "indirect bias,'' has resisted prior attempts at

Allen Zang, Xinan Chen, Alexander Kolar, Joaquin Chung

Quantum repeater networks that allow long-distance entanglement distribution will be the backbone of distributed quantum information processing. In this paper we explore entanglement distribution using quantum repeaters with optimized buffer time, equipped with noisy quantum memories and performing imperfect entanglement purification and swapping. We observe

Raktim Abir, Igor Akushevich, Tolga Altinoluk, Daniele Paolo Anderle

We outline the physics opportunities provided by the Electron Ion Collider (EIC). These include the study of the parton structure of the nucleon and nuclei, the onset of gluon saturation, the production of jets and heavy flavor, hadron spectroscopy and tests of fundamental symmetries. We review the present status and future challenges in EIC theory that have

Li Sun, Florian Luisier, Kayhan Batmanghelich, Dinei Florencio

Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens. This process known as tokenization relies on a pre-built vocabulary of words or sub-word morphemes. This fixed vocabulary limits the model's robustness to spelling errors and its capacity to adapt to new domains. In this w

Tony G. Chen, Billie C. Goolsby, Guadalupe Bernal, Lauren A. O'Connell

We present the design and operation of tadpole-mimetic robots prepared for a study of the parenting behaviors of poison frogs, which pair bond and raise their offspring. The mission of these robots is to convince poison frog parents that they are tadpoles, which need to be fed. Tadpoles indicate this need, at least in part, by wriggling with a characteristic

Srijan Bansal, Semih Yavuz, Bo Pang, Meghana Bhat

Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks. While recent research has explored the idea of unified QA models, such models are usually explored for high-resource scenarios and require re-training to extend their capab

Jiahui Liu, Xiaohao Cai, Mahesan Niranjan

Linear discriminant analysis (LDA) has been a useful tool in pattern recognition and data analysis research and practice. While linearity of class boundaries cannot always be expected, nonlinear projections through pre-trained deep neural networks have served to map complex data onto feature spaces in which linear discrimination has served well. The solution

Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio

Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty. Recent state-of-the-art methods, however, leverage expensive attention mechanisms, limiting their applications, particularly in low-resource settings. In this work, we propose Constant Memory Attentive Neural Processes (CMANPs), an NP variant that only

M. Zaki Jawaid, Robin W. Yeo, Aayushma Gautam, T. Blair Gainous

Designing novel functional proteins remains a slow and expensive process due to a variety of protein engineering challenges; in particular, the number of protein variants that can be experimentally tested in a given assay pales in comparison to the vastness of the overall sequence space, resulting in low hit rates and expensive wet lab testing cycles. In thi